{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T15:52:28Z","timestamp":1782489148259,"version":"3.54.5"},"reference-count":1654,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2021,3,31]],"date-time":"2021-03-31T00:00:00Z","timestamp":1617148800000},"content-version":"vor","delay-in-days":30,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,3,31]],"date-time":"2021-03-31T00:00:00Z","timestamp":1617148800000},"content-version":"tdm","delay-in-days":30,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"crossref","award":["EP\/N035437\/1"],"award-info":[{"award-number":["EP\/N035437\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2021,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Deep learning is transforming most areas of science and technology, including electron microscopy. This review paper offers a practical perspective aimed at developers with limited familiarity. For context, we review popular applications of deep learning in electron microscopy. Following, we discuss hardware and software needed to get started with deep learning and interface with electron microscopes. We then review neural network components, popular architectures, and their optimization. Finally, we discuss future directions of deep learning in electron microscopy.<\/jats:p>","DOI":"10.1088\/2632-2153\/abd614","type":"journal-article","created":{"date-parts":[[2020,12,22]],"date-time":"2020-12-22T22:38:57Z","timestamp":1608676737000},"page":"011004","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":78,"title":["Deep learning in electron microscopy"],"prefix":"10.1088","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9358-5364","authenticated-orcid":false,"given":"Jeffrey M","family":"Ede","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2021,3,31]]},"reference":[{"key":"mlstabd614bib1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aam9744","article-title":"There\u2019s plenty of room at the top: what will drive computer performance after Moore\u2019s law?","volume":"368","author":"Leiserson","year":"2020","journal-title":"Science"},{"key":"mlstabd614bib2","first-page":"843","article-title":"Revisiting unreasonable effectiveness of data in deep learning era","author":"Sun","year":"2017"},{"key":"mlstabd614bib3","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2019.0054","article-title":"Machine learning and big scientific data","volume":"378","author":"Hey","year":"2020","journal-title":"Phil. Trans. R. Soc. A"},{"key":"mlstabd614bib4","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.105596","article-title":"A review of deep learning with special emphasis on architectures, applications and recent trends","volume":"4","author":"Sengupta","year":"2020","journal-title":"Knowl.-Based Syst."},{"key":"mlstabd614bib5","doi-asserted-by":"publisher","first-page":"53040","DOI":"10.1109\/ACCESS.2019.2912200","article-title":"Review of deep learning algorithms and architectures","volume":"7","author":"Shrestha","year":"2019","journal-title":"IEEE Access"},{"key":"mlstabd614bib6","first-page":"1071","article-title":"A survey of deep learning and its applications: a new paradigm to machine learning","volume":"2","author":"Dargan","year":"2019","journal-title":"Archives Computat. Methods Eng."},{"key":"mlstabd614bib7","doi-asserted-by":"publisher","first-page":"292","DOI":"10.3390\/electronics8030292","article-title":"A state-of-the-art survey on deep learning theory and architectures","volume":"8","author":"Alom","year":"2019","journal-title":"Electronics"},{"key":"mlstabd614bib8","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.inffus.2017.10.006","article-title":"A survey on deep learning for big data","volume":"42","author":"Zhang","year":"2018","journal-title":"Inform. Fusion"},{"key":"mlstabd614bib9","doi-asserted-by":"publisher","first-page":"24411","DOI":"10.1109\/ACCESS.2018.2830661","article-title":"A survey of deep learning: platforms, applications and emerging research trends","volume":"6","author":"Hatcher","year":"2018","journal-title":"IEEE Access"},{"key":"mlstabd614bib10","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"mlstabd614bib11","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep learning in neural networks: an overview","volume":"61","author":"Schmidhuber","year":"2015","journal-title":"Neural Netw."},{"key":"mlstabd614bib12","doi-asserted-by":"publisher","DOI":"10.1016\/j.mtnano.2020.100087","article-title":"Deep learning analysis on microscopic imaging in materials science","volume":"11","author":"Ge","year":"2020","journal-title":"Mater. Today Nano"},{"key":"mlstabd614bib13","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.91.045002","article-title":"Machine learning and the physical sciences","volume":"91","author":"Carleo","year":"2019","journal-title":"Rev. Mod. Phys."},{"key":"mlstabd614bib14","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1002\/inf2.12028","article-title":"Machine learning in materials science","volume":"1","author":"Wei","year":"2019","journal-title":"InfoMat"},{"key":"mlstabd614bib15","doi-asserted-by":"publisher","first-page":"921","DOI":"10.1364\/OPTICA.6.000921","article-title":"On the use of deep learning for computational imaging","volume":"6","author":"Barbastathis","year":"2019","journal-title":"Optica"},{"key":"mlstabd614bib16","doi-asserted-by":"publisher","DOI":"10.1088\/2515-7639\/ab084b","article-title":"From DFT to machine learning: recent approaches to materials science\u2014a review","volume":"2","author":"Schleder","year":"2019","journal-title":"J. Phys.: Mater."},{"key":"mlstabd614bib17","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ab6d5d","article-title":"Introducing machine learning: science and technology","volume":"1","author":"von Lilienfeld","year":"2020","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstabd614bib18","author":"Sejnowski","year":"2018"},{"key":"mlstabd614bib19","author":"Alom","year":"2018"},{"key":"mlstabd614bib20","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1037\/pspa0000098","article-title":"Deep neural networks are more accurate than humans at detecting sexual orientation from facial images","volume":"114","author":"Wang","year":"2018","journal-title":"J. Pers. Soc. Psychol."},{"key":"mlstabd614bib21","doi-asserted-by":"publisher","DOI":"10.1038\/srep32672","article-title":"Deep networks can resemble human feed-forward vision in invariant object recognition","volume":"6","author":"Kheradpisheh","year":"2016","journal-title":"Sci. Rep."},{"key":"mlstabd614bib22","first-page":"1026","article-title":"Delving deep into rectifiers: surpassing human-level performance on imagenet classification","author":"He","year":"2015"},{"key":"mlstabd614bib23","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v29i1.9797","article-title":"Surpassing human-level face verification performance on LFW with gaussianface","author":"Lu","year":"2015"},{"key":"mlstabd614bib24","article-title":"AlphaStar: mastering the real-time strategy game StarCraft II","author":"Vinyals","year":"2019"},{"key":"mlstabd614bib25","author":"Firoiu","year":"2017"},{"key":"mlstabd614bib26","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.10827","article-title":"Playing FPS games with deep reinforcement learning","author":"Lample","year":"2017"},{"key":"mlstabd614bib27","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"Silver","year":"2016","journal-title":"Nature"},{"key":"mlstabd614bib28","author":"Mnih","year":"2013"},{"key":"mlstabd614bib29","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(01)00110-2","article-title":"Programming backgammon using self-teaching neural nets","volume":"134","author":"Tesauro","year":"2002","journal-title":"Artif. Intell."},{"key":"mlstabd614bib30","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0191493","article-title":"Deep neural networks show an equivalent and often superior performance to dermatologists in onychomycosis diagnosis: automatic construction of onychomycosis datasets by region-based convolutional deep neural network","volume":"13","author":"Han","year":"2018","journal-title":"PLoS One"},{"key":"mlstabd614bib31","author":"Wang","year":"2016"},{"key":"mlstabd614bib32","first-page":"4967","article-title":"A simple neural network module for relational reasoning","author":"Santoro","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"mlstabd614bib33","author":"Xiong","year":"2016"},{"key":"mlstabd614bib34","first-page":"5632","article-title":"Single-channel mixed speech recognition using deep neural networks","author":"Weng","year":"2014"},{"key":"mlstabd614bib35","author":"Lee","year":"2017"},{"key":"mlstabd614bib36","first-page":"37","article-title":"Planet-photo geolocation with convolutional neural networks","author":"Weyand","year":"2016"},{"key":"mlstabd614bib37","author":"Kidger","year":"2019"},{"key":"mlstabd614bib38","first-page":"6169","article-title":"ResNet with one-neuron hidden layers is a universal approximator","author":"Lin","year":"2018"},{"key":"mlstabd614bib39","author":"Hanin","year":"2017"},{"key":"mlstabd614bib40","first-page":"6231","article-title":"The expressive power of neural networks: a view from the width","author":"Lu","year":"2017"},{"key":"mlstabd614bib41","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1017\/S0962492900002919","article-title":"Approximation theory of the MLP model in neural networks","volume":"8","author":"Pinkus","year":"1999","journal-title":"Acta Numer."},{"key":"mlstabd614bib42","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/S0893-6080(05)80131-5","article-title":"Multilayer feedforward networks with a nonpolynomial activation function can approximate any function","volume":"6","author":"Leshno","year":"1993","journal-title":"Neural Netw."},{"key":"mlstabd614bib43","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/0893-6080(91)90009-T","article-title":"Approximation capabilities of multilayer feedforward networks","volume":"4","author":"Hornik","year":"1991","journal-title":"Neural Netw."},{"key":"mlstabd614bib44","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural Netw."},{"key":"mlstabd614bib45","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/BF02551274","article-title":"Approximation by superpositions of a sigmoidal function","volume":"2","author":"Cybenko","year":"1989","journal-title":"Math. Control Signals Syst."},{"key":"mlstabd614bib46","article-title":"Deep, skinny neural networks are not universal approximators","author":"Johnson","year":"2018"},{"key":"mlstabd614bib47","doi-asserted-by":"publisher","first-page":"1223","DOI":"10.1007\/s10955-017-1836-5","article-title":"Why does deep and cheap learning work so well?","volume":"168","author":"Lin","year":"2017","journal-title":"J. Stat. Phys."},{"key":"mlstabd614bib48","article-title":"Expressivity of deep neural networks","author":"G\u00fchring","year":"2020"},{"key":"mlstabd614bib49","first-page":"2847","article-title":"On the expressive power of deep neural networks","author":"Raghu","year":"2017"},{"key":"mlstabd614bib50","first-page":"3360","article-title":"Exponential expressivity in deep neural networks through transient chaos","author":"Poole","year":"2016"},{"key":"mlstabd614bib51","first-page":"361","article-title":"Deep ReLU networks have surprisingly few activation patterns","author":"Hanin","year":"2019"},{"key":"mlstabd614bib52","first-page":"3349","article-title":"Generalization error bounds of gradient descent for learning over-parameterized deep ReLU networks","author":"Cao","year":"2020"},{"key":"mlstabd614bib53","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ab633c","article-title":"Scaling description of generalization with number of parameters in deep learning","volume":"2020","author":"Geiger","year":"2020","journal-title":"J. Stat. Mech.: Theory Exp."},{"key":"mlstabd614bib54","article-title":"Revisiting generalization for deep learning: PAC-Bayes, flat minima, and generative models","author":"Dziugaite","year":"2020"},{"key":"mlstabd614bib55","first-page":"10836","article-title":"Generalization bounds of stochastic gradient descent for wide and deep neural networks","author":"Cao","year":"2019"},{"key":"mlstabd614bib56","author":"Xu","year":"2018"},{"key":"mlstabd614bib57","first-page":"5947","article-title":"Exploring generalization in deep learning","author":"Neyshabur","year":"2017"},{"key":"mlstabd614bib58","author":"Wu","year":"2017"},{"key":"mlstabd614bib59","author":"Kawaguchi","year":"2017"},{"key":"mlstabd614bib60","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.124.010508","article-title":"Discovering physical concepts with neural networks","volume":"124","author":"Iten","year":"2020","journal-title":"Phys. Rev. Lett."},{"key":"mlstabd614bib61","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.100.033311","article-title":"Toward an artificial intelligence physicist for unsupervised learning","volume":"100","author":"Wu","year":"2019","journal-title":"Phys. Rev. E"},{"key":"mlstabd614bib62","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1016\/j.eng.2020.01.007","article-title":"A survey of accelerator architectures for deep neural networks","volume":"6","author":"Chen","year":"2020","journal-title":"Engineering"},{"key":"mlstabd614bib63","first-page":"613","article-title":"Hardware architectures for the fast fourier transform","author":"Garrido","year":"2019"},{"key":"mlstabd614bib64","first-page":"120","article-title":"Discrete fourier transform computation using neural networks","author":"Velik","year":"2008"},{"key":"mlstabd614bib65","first-page":"112","article-title":"The FFT on a GPU","author":"Moreland","year":"2003"},{"key":"mlstabd614bib66","doi-asserted-by":"publisher","first-page":"2465","DOI":"10.1093\/mnras\/staa713","article-title":"Newton versus the machine: solving the chaotic three-body problem using deep neural networks","volume":"494","author":"Breen","year":"2020","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstabd614bib67","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.100.022512","article-title":"Deep learning and density-functional theory","volume":"100","author":"Ryczko","year":"2019","journal-title":"Phys. Rev. A"},{"key":"mlstabd614bib68","article-title":"Deep neural network computes electron densities and energies of a large set of organic molecules faster than density functional theory (DFT)","author":"Sinitskiy","year":"2018"},{"key":"mlstabd614bib69","doi-asserted-by":"publisher","first-page":"19388","DOI":"10.1364\/OE.26.019388","article-title":"Fast phase retrieval in off-axis digital holographic microscopy through deep learning","volume":"26","author":"Zhang","year":"2018","journal-title":"Opt. Express"},{"key":"mlstabd614bib70","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.ultramic.2019.03.017","article-title":"Improving electron micrograph signal-to-noise with an atrous convolutional encoder\u2013decoder","volume":"202","author":"Ede","year":"2019","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib71","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012"},{"key":"mlstabd614bib72","article-title":"Improving electron micrograph signal-to-noise with an atrous convolutional encoder\u2013decoder","author":"Ede","year":"2018"},{"key":"mlstabd614bib73","author":"","year":"2020"},{"key":"mlstabd614bib74","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1176\/2\/022010","article-title":"Overview of image denoising based on deep learning","volume":"1176","author":"Liu","year":"2019"},{"key":"mlstabd614bib75","article-title":"Deep learning on image denoising: an overview","author":"Tian","year":"2019"},{"key":"mlstabd614bib76","doi-asserted-by":"publisher","first-page":"201","DOI":"10.4258\/hir.2019.25.3.201","article-title":"Deep learning-based electrocardiogram signal noise detection and screening model","volume":"25","author":"Yoon","year":"2019","journal-title":"Healthc. Inform. Res."},{"key":"mlstabd614bib77","article-title":"Deep recurrent neural networks for ECG signal denoising","author":"Antczak","year":"2018"},{"key":"mlstabd614bib78","article-title":"Probabilistic self-learning framework for low-dose CT denoising","author":"Bai","year":"2020"},{"key":"mlstabd614bib79","doi-asserted-by":"publisher","first-page":"704","DOI":"10.1007\/s11227-017-2080-0","article-title":"Medical image denoising using convolutional neural network: a residual learning approach","volume":"75","author":"Jifara","year":"2019","journal-title":"J. Supercomput."},{"key":"mlstabd614bib80","first-page":"85","article-title":"Speckle noise removal in ultrasound images using a deep convolutional neural network and a specially designed loss function","author":"Feng","year":"2019"},{"key":"mlstabd614bib81","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/JPROC.2019.2949575","article-title":"Deep-learning-based image reconstruction and enhancement in optical microscopy","volume":"108","author":"de Haan","year":"2019","journal-title":"Proc. IEEE"},{"key":"mlstabd614bib82","doi-asserted-by":"publisher","first-page":"3860","DOI":"10.1364\/BOE.10.003860","article-title":"Denoising of stimulated raman scattering microscopy images via deep learning","volume":"10","author":"Manifold","year":"2019","journal-title":"Biomed. Opt. Express"},{"key":"mlstabd614bib83","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-51062-7","article-title":"A deep learning approach to denoise optical coherence tomography images of the optic nerve head","volume":"9","author":"Devalla","year":"2019","journal-title":"Sci. Rep."},{"key":"mlstabd614bib84","doi-asserted-by":"publisher","first-page":"4927","DOI":"10.1364\/OE.27.004927","article-title":"Cycle-consistent deep learning approach to coherent noise reduction in optical diffraction tomography","volume":"27","author":"Choi","year":"2019","journal-title":"Opt. Express"},{"key":"mlstabd614bib85","doi-asserted-by":"crossref","DOI":"10.1016\/j.specom.2020.04.002","article-title":"A review of multi-objective deep learning speech denoising methods","author":"Azarang","year":"2020"},{"key":"mlstabd614bib86","article-title":"Phase-aware single-stage speech denoising and dereverberation with U-net","author":"Choi","year":"2020"},{"key":"mlstabd614bib87","article-title":"Self-supervised deep learning-based speech denoising","author":"Alamdari","year":"2019"},{"key":"mlstabd614bib88","doi-asserted-by":"publisher","first-page":"982","DOI":"10.1109\/TASLP.2015.2416653","article-title":"Learning spectral mapping for speech dereverberation and denoising","volume":"23","author":"Han","year":"2015","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"mlstabd614bib89","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.inffus.2019.09.003","article-title":"Image denoising review: from classical to state-of-the-art approaches","volume":"55","author":"Goyal","year":"2020","journal-title":"Inf. Fusion"},{"key":"mlstabd614bib90","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.3446627","article-title":"Image denoising: issues and challenges","author":"Girdher","year":"2019"},{"key":"mlstabd614bib91","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/s42492-019-0016-7","article-title":"Brief review of image denoising techniques","volume":"2","author":"Fan","year":"2019","journal-title":"Vis. Comput. Ind. Biomed. Art"},{"key":"mlstabd614bib92","first-page":"393","article-title":"Investigation on the effect of a gaussian blur in image filtering and segmentation","author":"Gedraite","year":"2011"},{"key":"mlstabd614bib93","first-page":"1615","article-title":"An adaptive gaussian filter for noise reduction and edge detection","author":"Deng","year":"1993"},{"key":"mlstabd614bib94","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1007\/s10278-018-0110-y","article-title":"An automatic parameter decision system of bilateral filtering with GPU-based acceleration for brain MR images","volume":"32","author":"Chang","year":"2019","journal-title":"J. Digit. Imaging"},{"key":"mlstabd614bib95","first-page":"108","article-title":"Image denoising using optimally weighted bilateral filters: a sure and fast approach","author":"Chaudhury","year":"2015"},{"key":"mlstabd614bib96","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1016\/j.compmedimag.2014.06.012","article-title":"Adaptive-weighted bilateral filtering and other pre-processing techniques for optical coherence tomography","volume":"38","author":"Anantrasirichai","year":"2014","journal-title":"Comput. Med. Imaging Graph."},{"key":"mlstabd614bib97","first-page":"839","article-title":"Bilateral filtering for gray and color images","author":"Tomasi","year":"1998"},{"key":"mlstabd614bib98","doi-asserted-by":"publisher","first-page":"625","DOI":"10.13005\/bpj\/1415","article-title":"An efficient image denoising scheme for higher noise levels using spatial domain filters","volume":"11","author":"Budhiraja","year":"2018","journal-title":"Biomed. Pharmacol. J."},{"key":"mlstabd614bib99","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1186\/s13640-019-0444-5","article-title":"A robust anisotropic diffusion filter with low arithmetic complexity for images","volume":"2019","author":"Nair","year":"2019","journal-title":"EURASIP J. Image Video Process."},{"key":"mlstabd614bib100","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1109\/34.56205","article-title":"Scale-space and edge detection using anisotropic diffusion","volume":"12","author":"Perona","year":"1990","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstabd614bib101","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1109\/82.749102","article-title":"Progressive switching median filter for the removal of impulse noise from highly corrupted images","volume":"46","author":"Wang","year":"1999","journal-title":"IEEE Trans. Circuits Syst."},{"key":"mlstabd614bib102","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1109\/78.370615","article-title":"Optimal weighted median filtering under structural constraints","volume":"43","author":"Yang","year":"1995","journal-title":"IEEE Trans. Signal Process."},{"key":"mlstabd614bib103","doi-asserted-by":"publisher","first-page":"1782","DOI":"10.1093\/mnras\/stx527","article-title":"Wiener filter reloaded: fast signal reconstruction without preconditioning","volume":"468","author":"Kodi Ramanah","year":"2017","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstabd614bib104","doi-asserted-by":"publisher","first-page":"A111","DOI":"10.1051\/0004-6361\/201220586","article-title":"Efficient wiener filtering without preconditioning","volume":"549","author":"Elsner","year":"2013","journal-title":"Astron. Astrophys."},{"key":"mlstabd614bib105","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1111\/j.1365-2478.1967.tb01793.x","article-title":"Principles of digital wiener filtering","volume":"15","author":"Robinson","year":"1967","journal-title":"Geophys. Prospect."},{"key":"mlstabd614bib106","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.sigpro.2019.04.005","article-title":"An iterative wavelet threshold for signal denoising","volume":"162","author":"Bayer","year":"2019","journal-title":"Signal Process."},{"key":"mlstabd614bib107","first-page":"213","article-title":"Image de-noising using discrete wavelet transform","volume":"8","author":"Mohideen","year":"2008","journal-title":"Int. J. Comput. Sci. Netw. Secur."},{"key":"mlstabd614bib108","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1109\/TIP.2007.891064","article-title":"A new sure approach to image denoising: interscale orthonormal wavelet thresholding","volume":"16","author":"Luisier","year":"2007","journal-title":"IEEE Trans. Image Process."},{"key":"mlstabd614bib109","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1198\/016214501753168307","article-title":"Empirical bayes approach to improve wavelet thresholding for image noise reduction","volume":"96","author":"Jansen","year":"2001","journal-title":"J. Am. Stat. Assoc."},{"key":"mlstabd614bib110","doi-asserted-by":"publisher","first-page":"1532","DOI":"10.1109\/83.862633","article-title":"Adaptive wavelet thresholding for image denoising and compression","volume":"9","author":"Chang","year":"2000","journal-title":"IEEE Trans. Image Process."},{"key":"mlstabd614bib111","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1093\/biomet\/81.3.425","article-title":"Ideal spatial adaptation by wavelet shrinkage","volume":"81","author":"Donoho","year":"1994","journal-title":"Biometrika"},{"key":"mlstabd614bib112","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1109\/MSP.2009.935453","article-title":"The curvelet transform","volume":"27","author":"Ma","year":"2010","journal-title":"IEEE Signal Process. Mag."},{"key":"mlstabd614bib113","doi-asserted-by":"crossref","first-page":"670","DOI":"10.1109\/TIP.2002.1014998","article-title":"The curvelet transform for image denoising","volume":"11","author":"Starck","year":"2002","journal-title":"IEEE Trans. Image Process."},{"key":"mlstabd614bib114","doi-asserted-by":"publisher","first-page":"3461","DOI":"10.3390\/e17053461","article-title":"Nonparametric denoising methods based on contourlet transform with sharp frequency localization: application to low exposure time electron microscopy images","volume":"17","author":"Ahmed","year":"2015","journal-title":"Entropy"},{"key":"mlstabd614bib115","doi-asserted-by":"publisher","first-page":"2091","DOI":"10.1109\/TIP.2005.859376","article-title":"The contourlet transform: an efficient directional multiresolution image representation","volume":"14","author":"Do","year":"2005","journal-title":"IEEE Trans. Image Process."},{"key":"mlstabd614bib116","first-page":"501","article-title":"Wavelet packet based ct image denoising using bilateral method and bayes shrinkage rule","author":"Diwakar","year":"2019"},{"key":"mlstabd614bib117","first-page":"220","article-title":"Hybrid method for medical image denoising using shearlet transform and bilateral filter","author":"Thakur","year":"2015"},{"key":"mlstabd614bib118","first-page":"5641","article-title":"Image de-noising by using median filter and weiner filter","volume":"2","author":"Nagu","year":"2014","journal-title":"Image"},{"key":"mlstabd614bib119","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.infrared.2013.12.007","article-title":"Spatial and temporal bilateral filter for infrared small target enhancement","volume":"63","author":"Bae","year":"2014","journal-title":"Infrared Phys. Technol."},{"key":"mlstabd614bib120","first-page":"440","article-title":"Dual-domain image denoising","author":"Knaus","year":"2013"},{"key":"mlstabd614bib121","doi-asserted-by":"publisher","first-page":"1715","DOI":"10.1109\/TIP.2011.2176954","article-title":"BM3D frames and variational image deblurring","volume":"21","author":"Danielyan","year":"2011","journal-title":"IEEE Trans. Image Process."},{"key":"mlstabd614bib122","doi-asserted-by":"publisher","first-page":"2080","DOI":"10.1109\/TIP.2007.901238","article-title":"Image denoising by sparse 3-D transform-domain collaborative filtering","volume":"16","author":"Dabov","year":"2007","journal-title":"IEEE Trans. Image Process."},{"key":"mlstabd614bib123","doi-asserted-by":"publisher","first-page":"22514","DOI":"10.1109\/ACCESS.2017.2762760","article-title":"Image denoising via sparse representation over grouped dictionaries with adaptive atom size","volume":"5","author":"Jia","year":"2017","journal-title":"IEEE Access"},{"key":"mlstabd614bib124","doi-asserted-by":"publisher","first-page":"1001","DOI":"10.1109\/TCYB.2013.2278548","article-title":"From heuristic optimization to dictionary learning: a review and comprehensive comparison of image denoising algorithms","volume":"44","author":"Shao","year":"2013","journal-title":"IEEE Trans. Cybern."},{"key":"mlstabd614bib125","doi-asserted-by":"publisher","first-page":"1438","DOI":"10.1109\/TIP.2009.2018575","article-title":"Clustering-based denoising with locally learned dictionaries","volume":"18","author":"Chatterjee","year":"2009","journal-title":"IEEE Trans. Image Process."},{"key":"mlstabd614bib126","doi-asserted-by":"publisher","first-page":"4311","DOI":"10.1109\/TSP.2006.881199","article-title":"K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation","volume":"54","author":"Aharon","year":"2006","journal-title":"IEEE Trans. Signal Process."},{"key":"mlstabd614bib127","doi-asserted-by":"publisher","first-page":"3736","DOI":"10.1109\/TIP.2006.881969","article-title":"Image denoising via sparse and redundant representations over learned dictionaries","volume":"15","author":"Elad","year":"2006","journal-title":"IEEE Trans. Image Process."},{"key":"mlstabd614bib128","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.122.083603","article-title":"Shot-noise-limited nanomechanical detection and radiation pressure backaction from an electron beam","volume":"122","author":"Pairis","year":"2019","journal-title":"Phys. Rev. Lett."},{"key":"mlstabd614bib129","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1016\/j.ultramic.2018.06.014","article-title":"Theoretical framework of statistical noise in scanning transmission electron microscopy","volume":"193","author":"Seki","year":"2018","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib130","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.ultramic.2014.01.010","article-title":"Electron dose dependence of signal-to-noise ratio, atom contrast and resolution in transmission electron microscope images","volume":"145","author":"Lee","year":"2014","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib131","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1002\/sca.20282","article-title":"A statistical model of signal\u2013noise in scanning electron microscopy","volume":"34","author":"Timischl","year":"2012","journal-title":"Scanning"},{"key":"mlstabd614bib132","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1002\/sca.4950260106","article-title":"Effect of shot noise and secondary emission noise in scanning electron microscope images","volume":"26","author":"Sim","year":"2004","journal-title":"Scanning"},{"key":"mlstabd614bib133","doi-asserted-by":"crossref","DOI":"10.5121\/sipij.2015.6206","article-title":"A review paper: noise models in digital image processing","author":"Boyat","year":"2015"},{"key":"mlstabd614bib134","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1002\/(SICI)1097-0029(20000501)49:3269::AID-JEMT53.0.CO;2-B","article-title":"Characterisation of the signal and noise transfer of CCD cameras for electron detection","volume":"49","author":"Meyer","year":"2000","journal-title":"Microsc. Res. Tech."},{"key":"mlstabd614bib135","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1016\/0304-3991(92)90026-G","article-title":"Performance of a low-noise ccd camera adapted to a transmission electron microscope","volume":"46","author":"Kujawa","year":"1992","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib136","doi-asserted-by":"publisher","DOI":"10.1088\/0031-8949\/9\/1\/014107","article-title":"Optics of high-performance electron microscopes","volume":"9","author":"Rose","year":"2008","journal-title":"Sci. Technol. Adv. Mater."},{"key":"mlstabd614bib137","doi-asserted-by":"crossref","first-page":"8123","DOI":"10.1007\/s10853-020-04602-w","article-title":"Understanding of scanning-system distortions of atomic-scale scanning transmission electron microscopy images for accurate lattice parameter measurements","volume":"55","author":"Fujinaka","year":"2020","journal-title":"J. Mater. Sci."},{"key":"mlstabd614bib138","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40679-016-0020-3","article-title":"Dynamic scan control in stem: spiral scans","volume":"2","author":"Sang","year":"2016","journal-title":"Adv. Struct. Chem. Imaging"},{"key":"mlstabd614bib139","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1016\/j.ultramic.2017.09.003","article-title":"Scanning distortion correction in stem images","volume":"184","author":"Ning","year":"2018","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib140","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ultramic.2015.12.002","article-title":"Correcting nonlinear drift distortion of scanning probe and scanning transmission electron microscopies from image pairs with orthogonal scan directions","volume":"162","author":"Ophus","year":"2016","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib141","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1017\/S1431927613001402","article-title":"Identifying and correcting scan noise and drift in the scanning transmission electron microscope","volume":"19","author":"Jones","year":"2013","journal-title":"Microsc. Microanal."},{"key":"mlstabd614bib142","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1016\/j.jnucmat.2011.03.024","article-title":"In situ transmission electron microscopy of electron-beam induced damage process in nuclear grade graphite","volume":"412","author":"Karthik","year":"2011","journal-title":"J. Nucl. Mater."},{"key":"mlstabd614bib143","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-020-14529-0","article-title":"An interactive ImageJ plugin for semi-automated image denoising in electron microscopy","volume":"11","author":"Roels","year":"2020","journal-title":"Nat. Commun."},{"key":"mlstabd614bib144","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/j.jsb.2008.04.006","article-title":"Evaluation of denoising algorithms for biological electron tomography","volume":"164","author":"Narasimha","year":"2008","journal-title":"J. Struct. Biol."},{"key":"mlstabd614bib145","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1186\/s40679-015-0004-8","article-title":"Poisson noise removal from high-resolution stem images based on periodic block matching","volume":"1","author":"Mevenkamp","year":"2015","journal-title":"Adv. Struct. Chem. Imaging"},{"key":"mlstabd614bib146","first-page":"123","article-title":"Blind restoration of images degraded with mixed poisson-gaussian noise with application in transmission electron microscopy","author":"Baji\u0107","year":"2016"},{"key":"mlstabd614bib147","article-title":"Image denoising with less artefacts: novel non-linear filtering on fast patch reorderings","author":"Bodduna","year":"2020"},{"key":"mlstabd614bib148","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1016\/j.jsb.2016.04.007","article-title":"Denoising of high-resolution single-particle electron-microscopy density maps by their approximation using three-dimensional gaussian functions","volume":"194","author":"Joni\u0107","year":"2016","journal-title":"J. Struct. Biol."},{"key":"mlstabd614bib149","doi-asserted-by":"crossref","DOI":"10.4310\/AMSA.2020.v5.n2.a4","article-title":"Two-stage dimension reduction for noisy high-dimensional images and application to cryogenic electron microscopy","author":"Chung","year":"2020"},{"key":"mlstabd614bib150","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1007\/s11427-013-4467-3","article-title":"A Zernike-moment-based non-local denoising filter for cryo-em images","volume":"56","author":"Wang","year":"2013","journal-title":"Sci. China Life Sci."},{"key":"mlstabd614bib151","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/j.ultramic.2016.05.005","article-title":"Denoising time-resolved microscopy image sequences with singular value thresholding","volume":"178","author":"Furnival","year":"2017","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib152","doi-asserted-by":"publisher","first-page":"1205","DOI":"10.1016\/j.patcog.2005.12.009","article-title":"Improved Bayesian image denoising based on wavelets with applications to electron microscopy","volume":"39","author":"Sorzano","year":"2006","journal-title":"Pattern Recognit."},{"key":"mlstabd614bib153","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/s12900-018-0094-3","article-title":"Cryo-electron microscope image denoising based on the geodesic distance","volume":"18","author":"Ouyang","year":"2018","journal-title":"BMC Struct. Biol."},{"key":"mlstabd614bib154","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.ultramic.2014.11.012","article-title":"A nonlinear filtering algorithm for denoising HR (S)TEM micrographs","volume":"151","author":"Du","year":"2015","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib155","first-page":"276","article-title":"De-noising filters for TEM (transmission electron microscopy) image of nanomaterials","author":"Kushwaha","year":"2012"},{"key":"mlstabd614bib156","first-page":"379","article-title":"Maximum entropy restoration of electron microscope images with a random-spatial-distribution constraint","volume":"11","author":"Hanai","year":"1997","journal-title":"Scanning Microsc."},{"key":"mlstabd614bib157","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.ultramic.2017.03.020","article-title":"The impact of stem aberration correction on materials science","volume":"180","author":"Pennycook","year":"2017","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib158","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.ultramic.2017.03.016","article-title":"Twenty years after: how \u2018aberration correction in the stem\u2019 truly placed a \u2018a synchrotron in a microscope\u2019","volume":"180","author":"Ramasse","year":"2017","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib159","doi-asserted-by":"publisher","first-page":"3637","DOI":"10.1098\/rsta.2009.0004","article-title":"Aberration correction past and present","volume":"367","author":"Hawkes","year":"2009","journal-title":"Philos. Trans. R. Soc. A"},{"key":"mlstabd614bib160","doi-asserted-by":"crossref","DOI":"10.1017\/S1431927620001427","article-title":"Atomic-resolution cryo-stem across continuously variable temperature","author":"Goodge","year":"2020"},{"key":"mlstabd614bib161","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/j.micron.2019.01.005","article-title":"Radiation damage to organic and inorganic specimens in the TEM","volume":"119","author":"Egerton","year":"2019","journal-title":"Micron"},{"key":"mlstabd614bib162","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/j.ultramic.2012.07.006","article-title":"Control of radiation damage in the TEM","volume":"127","author":"Egerton","year":"2013","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib163","doi-asserted-by":"publisher","first-page":"1550","DOI":"10.1002\/jemt.22099","article-title":"Mechanisms of radiation damage in beam-sensitive specimens, for tem accelerating voltages between 10 and 300 kV","volume":"75","author":"Egerton","year":"2012","journal-title":"Microsc. Res. Tech."},{"key":"mlstabd614bib164","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/bs.aiep.2019.08.003","article-title":"Electron optics for a multi-pass transmission electron microscope","volume":"212","author":"Mankos","year":"2019","journal-title":"Adv. Imaging Electron Phys."},{"key":"mlstabd614bib165","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultramic.2019.112834","article-title":"Design for a 10 keV multi-pass transmission electron microscope","volume":"207","author":"Koppell","year":"2019","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib166","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-017-01841-x","article-title":"Multi-pass transmission electron microscopy","volume":"7","author":"Juffmann","year":"2017","journal-title":"Sci. Rep."},{"key":"mlstabd614bib167","doi-asserted-by":"publisher","first-page":"i98\u2013i113","DOI":"10.1093\/jmicro\/dfx125","article-title":"Managing dose-, damage- and data-rates in multi-frame spectrum-imaging","volume":"67","author":"Jones","year":"2018","journal-title":"Microscopy"},{"key":"mlstabd614bib168","first-page":"2129","article-title":"Noise2Void\u2014learning denoising from single noisy images","author":"Krull","year":"2019"},{"key":"mlstabd614bib169","first-page":"1712","article-title":"Toward convolutional blind denoising of real photographs","author":"Guo","year":"2019"},{"key":"mlstabd614bib170","first-page":"3204","article-title":"Universal denoising networks: a novel cnn architecture for image denoising","author":"Lefkimmiatis","year":"2018"},{"key":"mlstabd614bib171","doi-asserted-by":"publisher","first-page":"1090","DOI":"10.1038\/s41592-018-0216-7","article-title":"Content-aware image restoration: pushing the limits of fluorescence microscopy","volume":"15","author":"Weigert","year":"2018","journal-title":"Nat. Methods"},{"key":"mlstabd614bib172","doi-asserted-by":"publisher","first-page":"4608","DOI":"10.1109\/TIP.2018.2839891","article-title":"FFDNet: toward a fast and flexible solution for cnn-based image denoising","volume":"27","author":"Zhang","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"mlstabd614bib173","first-page":"126","article-title":"Isotropic reconstruction of 3D fluorescence microscopy images using convolutional neural networks","author":"Weigert","year":"2017"},{"key":"mlstabd614bib174","doi-asserted-by":"publisher","first-page":"3142","DOI":"10.1109\/TIP.2017.2662206","article-title":"Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising","volume":"26","author":"Zhang","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"mlstabd614bib175","first-page":"4539","article-title":"MemNet: a persistent memory network for image restoration","author":"Tai","year":"2017"},{"key":"mlstabd614bib176","first-page":"2802","article-title":"Image restoration using very deep convolutional encoder\u2013decoder networks with symmetric skip connections","author":"Mao","year":"2016"},{"key":"mlstabd614bib177","first-page":"502","article-title":"Cryo-CARE: content-aware image restoration for cryo-transmission electron microscopy data","author":"Buchholz","year":"2019"},{"key":"mlstabd614bib178","doi-asserted-by":"crossref","DOI":"10.1101\/740548","article-title":"Deep learning-based point-scanning super-resolution imaging","author":"Fang","year":"2019"},{"key":"mlstabd614bib179","article-title":"Deep denoising for scientific discovery: a case study in electron microscopy","author":"Mohan","year":"2020"},{"key":"mlstabd614bib180","doi-asserted-by":"publisher","DOI":"10.1016\/j.mee.2019.111051","article-title":"Deep learning denoising of sem images towards noise-reduced ler measurements","volume":"216","author":"Giannatou","year":"2019","journal-title":"Microelectron. Eng."},{"key":"mlstabd614bib181","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMM.18.2.024001","article-title":"Line roughness estimation and poisson denoising in scanning electron microscope images using deep learning","volume":"18","author":"Chaudhary","year":"2019","journal-title":"J. Micro. Nanolithogr. MEMS MOEMS"},{"key":"mlstabd614bib182","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1017\/S1431927619001685","article-title":"Deep learning as a tool for image denoising and drift correction","volume":"25","author":"Vasudevan","year":"2019","journal-title":"Microsc. Microanal."},{"key":"mlstabd614bib183","article-title":"Noise2Atom: unsupervised denoising for scanning transmission electron microscopy images","author":"Wang","year":"2020","journal-title":"Res. Square"},{"key":"mlstabd614bib184","doi-asserted-by":"crossref","DOI":"10.1101\/838920","article-title":"Topaz-denoise: general deep denoising models for cryoEM","author":"Bepler","year":"2019"},{"key":"mlstabd614bib185","first-page":"2965","article-title":"Noise2Noise: learning image restoration without clean data","author":"Lehtinen","year":"2018"},{"key":"mlstabd614bib186","doi-asserted-by":"publisher","first-page":"1146","DOI":"10.1038\/s41592-019-0580-y","article-title":"Real-time cryo-electron microscopy data preprocessing with warp","volume":"16","author":"Tegunov","year":"2019","journal-title":"Nat. Methods"},{"key":"mlstabd614bib187","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1017\/S1431927617001507","article-title":"Joint denoising and distortion correction for atomic column detection in scanning transmission electron microscopy images","volume":"23","author":"Zhang","year":"2017","journal-title":"Microsc. Microanal."},{"key":"mlstabd614bib188","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1111\/jmi.12293","article-title":"Correction of image drift and distortion in a scanning electron microscopy","volume":"260","author":"Jin","year":"2015","journal-title":"J. Microsc."},{"key":"mlstabd614bib189","doi-asserted-by":"publisher","first-page":"4062","DOI":"10.1109\/JSTARS.2019.2937690","article-title":"Image registration with Fourier-based image correlation: a comprehensive review of developments and applications","volume":"12","author":"Tong","year":"2019","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"mlstabd614bib190","doi-asserted-by":"crossref","DOI":"10.1101\/2020.04.05.026567","article-title":"Optical aberration correction via phase diversity and deep learning","author":"Krishnan","year":"2020"},{"key":"mlstabd614bib191","doi-asserted-by":"publisher","first-page":"14511","DOI":"10.1364\/OE.390856","article-title":"Direct determination of aberration functions in microscopy by an artificial neural network","volume":"28","author":"Cumming","year":"2020","journal-title":"Opt. Express"},{"key":"mlstabd614bib192","doi-asserted-by":"publisher","first-page":"26028","DOI":"10.1364\/OE.402109","article-title":"Correction of refractive index mismatch-induced aberrations under radially polarized illumination by deep learning","volume":"28","author":"Wang","year":"2020","journal-title":"Opt. Express"},{"key":"mlstabd614bib193","doi-asserted-by":"publisher","first-page":"10765","DOI":"10.1364\/OE.27.010765","article-title":"DNN-Based aberration correction in a wavefront sensorless adaptive optics system","volume":"27","author":"Tian","year":"2019","journal-title":"Opt. Express"},{"key":"mlstabd614bib194","doi-asserted-by":"publisher","first-page":"2354","DOI":"10.1021\/acsphotonics.8b00146","article-title":"Deep learning enhanced mobile-phone microscopy","volume":"5","author":"Rivenson","year":"2018","journal-title":"ACS Photonics"},{"key":"mlstabd614bib195","doi-asserted-by":"publisher","first-page":"15043","DOI":"10.1364\/OE.25.015043","article-title":"Automatic phase aberration compensation for digital holographic microscopy based on deep learning background detection","volume":"25","author":"Nguyen","year":"2017","journal-title":"Opt. Express"},{"key":"mlstabd614bib196","article-title":"Deep learning-based speed of sound aberration correction in photoacoustic images","volume":"vol 11240","author":"Jeon","year":"2020"},{"key":"mlstabd614bib197","article-title":"A review on generative adversarial networks: algorithms, theory, and applications","author":"Gui","year":"2020"},{"key":"mlstabd614bib198","article-title":"Generative adversarial networks (GANs): challenges, solutions, and future directions","author":"Saxena","year":"2020"},{"key":"mlstabd614bib199","doi-asserted-by":"publisher","first-page":"36322","DOI":"10.1109\/ACCESS.2019.2905015","article-title":"Recent progress on generative adversarial networks (GANs): a survey","volume":"7","author":"Pan","year":"2019","journal-title":"IEEE Access"},{"key":"mlstabd614bib200","article-title":"Generative adversarial networks: a survey and taxonomy","author":"Wang","year":"2019"},{"key":"mlstabd614bib201","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-65261-0","article-title":"Partial scanning transmission electron microscopy with deep learning","volume":"10","author":"Ede","year":"2020","journal-title":"Sci. Rep."},{"key":"mlstabd614bib202","article-title":"Deep learning supersampled scanning transmission electron microscopy","author":"Ede","year":"2019"},{"key":"mlstabd614bib203","article-title":"A Comparison study for image compression based on compressive sensing","volume":"vol 11373","author":"Atta","year":"2020"},{"key":"mlstabd614bib204","author":"Vidyasagar","year":"2019"},{"key":"mlstabd614bib205","doi-asserted-by":"publisher","first-page":"4875","DOI":"10.1109\/ACCESS.2018.2793851","article-title":"A systematic review of compressive sensing: concepts, implementations and applications","volume":"6","author":"Rani","year":"2018","journal-title":"IEEE Access"},{"key":"mlstabd614bib206","author":"Eldar","year":"2012"},{"key":"mlstabd614bib207","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1109\/TIT.2006.871582","article-title":"Compressed sensing","volume":"52","author":"Donoho","year":"2006","journal-title":"IEEE Trans. Inf. Theory"},{"key":"mlstabd614bib208","first-page":"p 12","article-title":"Improving the speed of MRI with artificial intelligence","volume":"vol 24","author":"Johnson","year":"2020"},{"key":"mlstabd614bib209","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s42490-019-0006-z","article-title":"Compressed sensing MRI: a review from signal processing perspective","volume":"1","author":"Ye","year":"2019","journal-title":"BMC Biomed. Eng."},{"key":"mlstabd614bib210","doi-asserted-by":"publisher","first-page":"1182","DOI":"10.1002\/mrm.21391","article-title":"Sparse MRI: the application of compressed sensing for rapid MR imaging","volume":"58","author":"Lustig","year":"2007","journal-title":"Magn. Reson. Med."},{"key":"mlstabd614bib211","doi-asserted-by":"publisher","first-page":"2889","DOI":"10.1109\/TMM.2020.2967646","article-title":"Image compression based on compressive sensing: end-to-end comparison with JPEG","volume":"22","author":"Yuan","year":"2020","journal-title":"IEEE Trans. Multimedia"},{"key":"mlstabd614bib212","first-page":"507","article-title":"Compressed sensing for image compression: survey of algorithms","author":"Gunasheela","year":"2019"},{"key":"mlstabd614bib213","article-title":"Deep learning for image super-resolution: a survey","author":"Wang","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstabd614bib214","doi-asserted-by":"publisher","first-page":"3106","DOI":"10.1109\/TMM.2019.2919431","article-title":"Deep learning for single image super-resolution: a brief review","volume":"21","author":"Yang","year":"2019","journal-title":"IEEE Trans. Multimedia"},{"key":"mlstabd614bib215","doi-asserted-by":"publisher","first-page":"356","DOI":"10.3348\/kjr.2019.0413","article-title":"Low-Dose abdominal CT using a deep learning-based denoising algorithm: a comparison with CT reconstructed with filtered back projection or iterative reconstruction algorithm","volume":"21","author":"Shin","year":"2020","journal-title":"Korean J. Radiol."},{"key":"mlstabd614bib216","article-title":"Deep-learning-based breast ct for radiation dose reduction","volume":"vol 11113","author":"Cong","year":"2019"},{"key":"mlstabd614bib217","first-page":"2195","article-title":"Adaptive compressed tomography sensing","author":"Barkan","year":"2013"},{"key":"mlstabd614bib218","doi-asserted-by":"crossref","DOI":"10.5220\/0008979603480356","article-title":"Robust perceptual night vision in thermal colorization","author":"Almasri","year":"2020"},{"key":"mlstabd614bib219","first-page":"3291","article-title":"Learning to see in the dark","author":"Chen","year":"2018"},{"key":"mlstabd614bib220","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.ultramic.2019.02.007","article-title":"The energy dependence of contrast and damage in electron cryomicroscopy of biological molecules","volume":"203","author":"Peet","year":"2019","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib221","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1016\/j.pmatsci.2018.03.002","article-title":"Radiation damage in nanostructured materials","volume":"96","author":"Zhang","year":"2018","journal-title":"Prog. Mater. Sci."},{"key":"mlstabd614bib222","doi-asserted-by":"publisher","DOI":"10.1063\/1.4973809","article-title":"Electron radiation damage mechanisms in 2D MoSe2","volume":"110","author":"Lehnert","year":"2017","journal-title":"Appl. Phys. Lett."},{"key":"mlstabd614bib223","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1017\/S1431927616000763","article-title":"The effect of electron beam irradiation in environmental scanning transmission electron microscopy of whole cells in liquid","volume":"22","author":"Hermannsd\u00f6rfer","year":"2016","journal-title":"Microsc. Microanal."},{"key":"mlstabd614bib224","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ultramic.2016.07.002","article-title":"Dose-rate-dependent damage of cerium dioxide in the scanning transmission electron microscope","volume":"170","author":"Johnston-Peck","year":"2016","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib225","author":"Jenkins","year":"2000"},{"key":"mlstabd614bib226","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1016\/j.micron.2004.02.003","article-title":"Radiation damage in the TEM and SEM","volume":"35","author":"Egerton","year":"2004","journal-title":"Micron"},{"key":"mlstabd614bib227","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.micron.2019.01.014","article-title":"Low dose scanning transmission electron microscopy of organic crystals by scanning moir\u00e9 fringes","volume":"120","author":"S\u2019ari","year":"2019","journal-title":"Micron"},{"key":"mlstabd614bib228","doi-asserted-by":"publisher","first-page":"3497","DOI":"10.1002\/cctc.201700519","article-title":"Cs-corrected STEM imaging of both pure and silver-supported metal-organic framework MIL-100 (Fe)","volume":"9","author":"Mayoral","year":"2017","journal-title":"ChemCatChem"},{"key":"mlstabd614bib229","doi-asserted-by":"publisher","DOI":"10.1098\/rsos.171838","article-title":"Quantification and optimization of ADF-STEM image contrast for beam-sensitive materials","volume":"5","author":"Gnanasekaran","year":"2018","journal-title":"R. Soc. Open Sci."},{"key":"mlstabd614bib230","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.micron.2019.01.013","article-title":"Cryo-analytical STEM of frozen, aqueous dispersions of nanoparticles","volume":"120","author":"Ilett","year":"2019","journal-title":"Micron"},{"key":"mlstabd614bib231","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ab9c3c","article-title":"Warwick electron microscopy datasets","volume":"1","author":"Ede","year":"2020","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstabd614bib232","doi-asserted-by":"publisher","first-page":"1701","DOI":"10.1109\/PROC.1967.5962","article-title":"Sampling, data transmission and the nyquist rate","volume":"55","author":"Landau","year":"1967","journal-title":"Proc. IEEE"},{"key":"mlstabd614bib233","doi-asserted-by":"publisher","DOI":"10.1098\/rsos.140550","article-title":"Sub-Nyquist artefacts and sampling moir\u00e9 effects","volume":"2","author":"Amidror","year":"2015","journal-title":"R. Soc. Open Sci."},{"key":"mlstabd614bib234","first-page":"70","article-title":"Image interpolation techniques in digital image processing: an overview","volume":"4","author":"Fadnavis","year":"2014","journal-title":"Int. J. Eng. Res. Appl."},{"key":"mlstabd614bib235","doi-asserted-by":"publisher","first-page":"238","DOI":"10.5201\/ipol.2011.g_lmii","article-title":"Linear methods for image interpolation","volume":"1","author":"Getreuer","year":"2011","journal-title":"Image Process. On Line"},{"key":"mlstabd614bib236","first-page":"147","author":"Turkowski","year":"1990"},{"key":"mlstabd614bib237","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1186\/s12911-016-0318-z","article-title":"Nearest neighbor imputation algorithms: a critical evaluation","volume":"16","author":"Beretta","year":"2016","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"mlstabd614bib238","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1016\/0167-8396(84)90029-3","article-title":"A trivariate clough\u2013tocher scheme for tetrahedral data","volume":"1","author":"Alfeld","year":"1984","journal-title":"Comput. Aided Geom. Des."},{"key":"mlstabd614bib239","doi-asserted-by":"publisher","first-page":"1376","DOI":"10.1109\/TIP.2017.2779265","article-title":"Single image super-resolution based on wiener filter in similarity domain","volume":"27","author":"Cruz","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"mlstabd614bib240","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1366\/1\/012097","article-title":"Rational bicubic ball for image interpolation","volume":"1366","author":"Zulkifli","year":"2019","journal-title":"J. Phys.: Conf. Series"},{"key":"mlstabd614bib241","article-title":"The magic kernel","author":"Costella","year":"2017"},{"key":"mlstabd614bib242","first-page":"25","article-title":"Nearest neighbor value interpolation","volume":"3","author":"Olivier","year":"2012","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"mlstabd614bib243","doi-asserted-by":"publisher","first-page":"i98","DOI":"10.1093\/jmicro\/dfx125","article-title":"Managing dose-, damage- and data-rates in multi-frame spectrum-imaging","volume":"67","author":"Jones","year":"2018","journal-title":"Microscopy"},{"key":"mlstabd614bib244","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.ultramic.2018.03.007","article-title":"How should a fixed budget of dwell time be spent in scanning electron microscopy to optimize image quality?","volume":"191","author":"Trampert","year":"2018","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib245","doi-asserted-by":"publisher","DOI":"10.1063\/1.5016192","article-title":"A sub-sampled approach to extremely low-dose STEM","volume":"112","author":"Stevens","year":"2018","journal-title":"Appl. Phys. Lett."},{"key":"mlstabd614bib246","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6501\/aa57df","article-title":"Towards the low-dose characterization of beam sensitive nanostructures via implementation of sparse image acquisition in scanning transmission electron microscopy","volume":"28","author":"Hwang","year":"2017","journal-title":"Meas. Sci. Technol."},{"key":"mlstabd614bib247","doi-asserted-by":"publisher","first-page":"778","DOI":"10.1017\/S1431927616011417","article-title":"Suppressing electron exposure artifacts: an electron scanning paradigm with bayesian machine learning","volume":"22","author":"Hujsak","year":"2016","journal-title":"Microsc. Microanal."},{"key":"mlstabd614bib248","article-title":"Sparse imaging for fast electron microscopy","volume":"vol 8657","author":"Anderson","year":"2013"},{"key":"mlstabd614bib249","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1093\/jmicro\/dft042","article-title":"The potential for bayesian compressive sensing to significantly reduce electron dose in high-resolution STEM images","volume":"63","author":"Stevens","year":"2013","journal-title":"Microscopy"},{"key":"mlstabd614bib250","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1088\/0266-5611\/23\/3\/008","article-title":"Sparsity and incoherence in compressive sampling","volume":"23","author":"Candes","year":"2007","journal-title":"Inverse Probl."},{"key":"mlstabd614bib251","doi-asserted-by":"publisher","DOI":"10.1063\/1.4965720","article-title":"Implementing an accurate and rapid sparse sampling approach for low-dose atomic resolution STEM imaging","volume":"109","author":"Kovarik","year":"2016","journal-title":"Appl. Phys. Lett."},{"key":"mlstabd614bib252","doi-asserted-by":"publisher","DOI":"10.1063\/1.4943086","article-title":"Development of a fast electromagnetic beam blanker for compressed sensing in scanning transmission electron microscopy","volume":"108","author":"B\u00e9ch\u00e9","year":"2016","journal-title":"Appl. Phys. Lett."},{"key":"mlstabd614bib253","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1017\/S143192761801543X","article-title":"Compressed sensing of scanning transmission electron microscopy (STEM) with nonrectangular scans","volume":"24","author":"Li","year":"2018","journal-title":"Microsc. Microanal."},{"key":"mlstabd614bib254","doi-asserted-by":"publisher","DOI":"10.1038\/srep43585","article-title":"Precision controlled atomic resolution scanning transmission electron microscopy using spiral scan pathways","volume":"7","author":"Sang","year":"2017","journal-title":"Sci. Rep."},{"key":"mlstabd614bib255","first-page":"1","article-title":"Survey on FPGA architecture and recent applications","author":"Gandhare","year":"2019"},{"key":"mlstabd614bib256","doi-asserted-by":"publisher","DOI":"10.1063\/1.5140721","article-title":"Deep learning for video compressive sensing","volume":"5","author":"Qiao","year":"2020","journal-title":"APL Photonics"},{"key":"mlstabd614bib257","article-title":"Deep compressed sensing","author":"Wu","year":"2019"},{"key":"mlstabd614bib258","first-page":"1","article-title":"Block-based compressed sensing of images via deep learning","author":"Adler","year":"2017"},{"key":"mlstabd614bib259","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-48444-2","article-title":"Resolution enhancement in scanning electron microscopy using deep learning","volume":"9","author":"de Haan","year":"2019","journal-title":"Sci. Rep."},{"key":"mlstabd614bib260","first-page":"1","article-title":"Deep learning for super-resolution in a field emission scanning electron microscope","volume":"1","author":"Gao","year":"2020","journal-title":"Artif. Intell."},{"key":"mlstabd614bib261","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ab81e2","article-title":"Adaptive learning rate clipping stabilizes learning","volume":"1","author":"Ede","year":"2020","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstabd614bib262","first-page":"548","article-title":"Super-resolution reconstruction of transmission electron microscopy images using deep learning","author":"Suveer","year":"2019"},{"key":"mlstabd614bib263","doi-asserted-by":"publisher","first-page":"1","DOI":"10.21928\/uhdjst.v4n1y2020.pp1-8","article-title":"Quality improvement for exemplar-based image inpainting using a modified searching mechanism","volume":"4","author":"Ahmed","year":"2020","journal-title":"UHD J. Sci. Technol."},{"key":"mlstabd614bib264","first-page":"817","author":"Pinjarkar","year":"2019"},{"key":"mlstabd614bib265","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1186\/s13640-019-0471-2","article-title":"Exemplar-based image inpainting using angle-aware patch matching","volume":"2019","author":"Zhang","year":"2019","journal-title":"EURASIP J. Image Video Process."},{"key":"mlstabd614bib266","doi-asserted-by":"publisher","first-page":"1200","DOI":"10.1109\/TIP.2004.833105","article-title":"Region filling and object removal by exemplar-based image inpainting","volume":"13","author":"Criminisi","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"mlstabd614bib267","doi-asserted-by":"publisher","first-page":"858","DOI":"10.3390\/electronics9050858","article-title":"A detection approach using LSTM-CNN for object removal caused by exemplar-based image inpainting","volume":"9","author":"Lu","year":"2020","journal-title":"Electronics"},{"key":"mlstabd614bib268","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1080\/10867651.2004.10487596","article-title":"An image inpainting technique based on the fast marching method","volume":"9","author":"Telea","year":"2004","journal-title":"J. Graph. Tools"},{"key":"mlstabd614bib269","first-page":"p I","article-title":"Navier\u2013Stokes, fluid dynamics and image and video inpainting","volume":"vol 1","author":"Bertalmio","year":"2001"},{"key":"mlstabd614bib270","first-page":"558","article-title":"Bag of tricks for image classification with convolutional neural networks","author":"He","year":"2019"},{"key":"mlstabd614bib271","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1109\/TEVC.2019.2916183","article-title":"Evolving deep convolutional neural networks for image classification","volume":"24","author":"Sun","year":"2019","journal-title":"IEEE Trans. Evol. Comput."},{"key":"mlstabd614bib272","doi-asserted-by":"publisher","first-page":"2352","DOI":"10.1162\/neco_a_00990","article-title":"Deep convolutional neural networks for image classification: a comprehensive review","volume":"29","author":"Rawat","year":"2017","journal-title":"Neural Comput."},{"key":"mlstabd614bib273","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1134\/S1054661816010065","article-title":"A survey of deep learning methods and software tools for image classification and object detection","volume":"26","author":"Druzhkov","year":"2016","journal-title":"Pattern Recognit. Image Anal."},{"key":"mlstabd614bib274","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1007\/s12551-020-00669-6","article-title":"Development of a deep learning-based method to identify \u2018good\u2019 regions of a cryo-electron microscopy grid","volume":"12","author":"Yokoyama","year":"2020","journal-title":"Biophys. Rev."},{"key":"mlstabd614bib275","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsb.2020.107498","article-title":"Micrographcleaner: a python package for cryo-em micrograph cleaning using deep learning","author":"Sanchez-Garcia","year":"2020","journal-title":"J. Struct. Biol."},{"key":"mlstabd614bib276","doi-asserted-by":"publisher","first-page":"eaaw1949","DOI":"10.1126\/sciadv.aaw1949","article-title":"Decoding crystallography from high-resolution electron imaging and diffraction datasets with deep learning","volume":"5","author":"Aguiar","year":"2019","journal-title":"Sci. Adv."},{"key":"mlstabd614bib277","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1038\/s41524-018-0086-7","article-title":"Mapping mesoscopic phase evolution during e-beam induced transformations via deep learning of atomically resolved images","volume":"4","author":"Vasudevan","year":"2018","journal-title":"npj Comput. Mater."},{"key":"mlstabd614bib278","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.3390\/molecules24061181","article-title":"Deep learning for validating and estimating resolution of cryo-electron microscopy density maps","volume":"24","author":"Avramov","year":"2019","journal-title":"Molecules"},{"key":"mlstabd614bib279","article-title":"Siamese neural networks for one-shot image recognition","volume":"vol 2","author":"Koch","year":"2015"},{"key":"mlstabd614bib280","first-page":"539","article-title":"Learning a similarity metric discriminatively, with application to face verification","volume":"vol 1","author":"Chopra","year":"2005"},{"key":"mlstabd614bib281","first-page":"737","article-title":"Signature verification using a \u2018siamese\u2019 time delay neural network","author":"Bromley","year":"1994"},{"key":"mlstabd614bib282","first-page":"4080","article-title":"Memory matching networks for one-shot image recognition","author":"Cai","year":"2018"},{"key":"mlstabd614bib283","doi-asserted-by":"publisher","first-page":"735","DOI":"10.1016\/j.cma.2019.01.005","article-title":"Predicting the effective mechanical property of heterogeneous materials by image based modeling and deep learning","volume":"347","author":"Li","year":"2019","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"mlstabd614bib284","doi-asserted-by":"publisher","first-page":"854","DOI":"10.1107\/S2052252518014392","article-title":"Deep consensus, a deep learning-based approach for particle pruning in cryo-electron microscopy","volume":"5","author":"Sanchez-Garcia","year":"2018","journal-title":"IUCrJ"},{"key":"mlstabd614bib285","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1016\/j.jsb.2016.07.006","article-title":"DeepPicker: a deep learning approach for fully automated particle picking in cryo-EM","volume":"195","author":"Wang","year":"2016","journal-title":"J. Struct. Biol."},{"key":"mlstabd614bib286","doi-asserted-by":"crossref","DOI":"10.1101\/2020.01.20.912139","article-title":"CASSPER: a semantic segmentation based particle picking algorithm for single particle cryo-electron microscopy","author":"George","year":"2020"},{"key":"mlstabd614bib287","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-49105-0","article-title":"Deep learning for semantic segmentation of defects in advanced stem images of steels","volume":"9","author":"Roberts","year":"2019","journal-title":"Sci. Rep."},{"key":"mlstabd614bib288","doi-asserted-by":"publisher","DOI":"10.1002\/adts.201800037","article-title":"A deep learning approach to identify local structures in atomic-resolution transmission electron microscopy images","volume":"1","author":"Madsen","year":"2018","journal-title":"Adv. Theory Simul."},{"key":"mlstabd614bib289","doi-asserted-by":"publisher","first-page":"12742","DOI":"10.1021\/acsnano.7b07504","article-title":"Deep learning of atomically resolved scanning transmission electron microscopy images: chemical identification and tracking local transformations","volume":"11","author":"Ziatdinov","year":"2017","journal-title":"ACS Nano"},{"key":"mlstabd614bib290","doi-asserted-by":"publisher","first-page":"eaaw8989","DOI":"10.1126\/sciadv.aaw8989","article-title":"Building and exploring libraries of atomic defects in graphene: scanning transmission electron and scanning tunneling microscopy study","volume":"5","author":"Ziatdinov","year":"2019","journal-title":"Sci. Adv."},{"key":"mlstabd614bib291","doi-asserted-by":"publisher","first-page":"3582","DOI":"10.1021\/nl801386m","article-title":"Direct imaging of lattice atoms and topological defects in graphene membranes","volume":"8","author":"Meyer","year":"2008","journal-title":"Nano Lett."},{"key":"mlstabd614bib292","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1038\/nmat2941","article-title":"Experimental analysis of charge redistribution due to chemical bonding by high-resolution transmission electron microscopy","volume":"10","author":"Meyer","year":"2011","journal-title":"Nat. Mater."},{"key":"mlstabd614bib293","doi-asserted-by":"publisher","first-page":"6544","DOI":"10.1038\/srep06544","article-title":"In situ atom scale visualization of domain wall dynamics in VO2 insulator-metal phase transition","volume":"4","author":"He","year":"2014","journal-title":"Sci. Rep."},{"key":"mlstabd614bib294","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.115.075501","article-title":"Experimental observation of quasicrystal growth","volume":"115","author":"Nagao","year":"2015","journal-title":"Phys. Rev. Lett."},{"key":"mlstabd614bib295","doi-asserted-by":"publisher","DOI":"10.1038\/srep40911","article-title":"Direct observation of the layer-by-layer growth of ZnO nanopillar by in situ high resolution transmission electron microscopy","volume":"7","author":"Li","year":"2017","journal-title":"Sci. Rep."},{"key":"mlstabd614bib296","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.micron.2013.12.011","article-title":"Atomic surface diffusion on Pt nanoparticles quantified by high-resolution transmission electron microscopy","volume":"63","author":"Schneider","year":"2014","journal-title":"Micron"},{"key":"mlstabd614bib297","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.ultramic.2017.12.018","article-title":"Determination of atomic positions from time resolved high resolution transmission electron microscopy images","volume":"186","author":"Hussaini","year":"2018","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib298","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1146\/annurev.bioeng.2.1.315","article-title":"Current methods in medical image segmentation","volume":"2","author":"Pham","year":"2000","journal-title":"Annu. Rev. Biomed. Eng."},{"key":"mlstabd614bib299","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.compmedimag.2013.12.005","article-title":"Biomedical image segmentation using geometric deformable models and metaheuristics","volume":"43","author":"Mesejo","year":"2015","journal-title":"Comput. Med. Imaging Graph."},{"key":"mlstabd614bib300","doi-asserted-by":"publisher","first-page":"961","DOI":"10.3233\/IFS-141378","article-title":"Image segmentation by generalized hierarchical fuzzy c-means algorithm","volume":"28","author":"Zheng","year":"2015","journal-title":"J. Intell. Fuzzy Syst."},{"key":"mlstabd614bib301","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1016\/j.neucom.2019.11.118","article-title":"A brief survey on semantic segmentation with deep learning","volume":"406","author":"Hao","year":"2020","journal-title":"Neurocomputing"},{"key":"mlstabd614bib302","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106062","article-title":"Evolution of image segmentation using deep convolutional neural network: a survey","volume":"201\u2013202","author":"Sultana","year":"2020","journal-title":"Knowl.-Based Syst."},{"key":"mlstabd614bib303","article-title":"Image segmentation using deep learning: a survey","author":"Minaee","year":"2020"},{"key":"mlstabd614bib304","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/s13735-017-0141-z","article-title":"A review of semantic segmentation using deep neural networks","volume":"7","author":"Guo","year":"2018","journal-title":"Int. J. Multimedia Inf. Retr."},{"key":"mlstabd614bib305","first-page":"801","article-title":"Encoder\u2013decoder with atrous separable convolution for semantic image segmentation","author":"Chen","year":"2018"},{"key":"mlstabd614bib306","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"mlstabd614bib307","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"SegNet: a deep convolutional encoder\u2013decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstabd614bib308","first-page":"234","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"mlstabd614bib309","first-page":"1205","article-title":"Adversarial-prediction guided multi-task adaptation for semantic segmentation of electron microscopy images","author":"Yi","year":"2020"},{"key":"mlstabd614bib310","doi-asserted-by":"crossref","DOI":"10.1101\/2020.02.03.933127","article-title":"EM-net: deep learning for electron microscopy image segmentation","author":"Khadangi","year":"2020"},{"key":"mlstabd614bib311","article-title":"Cost-efficient segmentation of electron microscopy images using active learning","author":"Roels","year":"2019"},{"key":"mlstabd614bib312","doi-asserted-by":"publisher","DOI":"10.1016\/j.commatsci.2019.109216","article-title":"High-Throughput, algorithmic determination of pore parameters from electron microscopy","volume":"171","author":"Yu","year":"2020","journal-title":"Comput. Mater. Sci."},{"key":"mlstabd614bib313","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1109\/TMI.2016.2613019","article-title":"Residual deconvolutional networks for brain electron microscopy image segmentation","volume":"36","author":"Fakhry","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstabd614bib314","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-55431-0","article-title":"UNI-EM: an environment for deep neural network-based automated segmentation of neuronal electron microscopic images","volume":"9","author":"Urakubo","year":"2019","journal-title":"Sci. Rep."},{"key":"mlstabd614bib315","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1017\/S1431927619001557","article-title":"DefectNet\u2014a deep convolutional neural network for semantic segmentation of crystallographic defects in advanced microscopy images","volume":"25","author":"Roberts","year":"2019","journal-title":"Microsc. Microanal."},{"key":"mlstabd614bib316","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.neunet.2019.08.025","article-title":"MultiResUNet: rethinking the U-Net architecture for multimodal biomedical image segmentation","volume":"121","author":"Ibtehaz","year":"2020","journal-title":"Neural Netw."},{"key":"mlstabd614bib317","article-title":"Methodologies for successful segmentation of HRTEM images via neural network","author":"Groschner","year":"2020"},{"key":"mlstabd614bib318","article-title":"Understanding important features of deep learning models for transmission electron microscopy image segmentation","author":"Horwath","year":"2019"},{"key":"mlstabd614bib319","doi-asserted-by":"publisher","first-page":"983","DOI":"10.1038\/nmeth.4405","article-title":"Convolutional neural networks for automated annotation of cellular cryo-electron tomograms","volume":"14","author":"Chen","year":"2017","journal-title":"Nat. Methods"},{"key":"mlstabd614bib320","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2972974","article-title":"Deep multi-modal object detection and semantic segmentation for autonomous driving: datasets, methods and challenges","author":"Feng","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"mlstabd614bib321","first-page":"1","article-title":"Lightningnet: fast and accurate semantic segmentation for autonomous driving based on 3D LIDAR point cloud","author":"Yang","year":"2020"},{"key":"mlstabd614bib322","first-page":"285","article-title":"Visual scene understanding for autonomous driving using semantic segmentation","author":"Hofmarcher","year":"2019"},{"key":"mlstabd614bib323","doi-asserted-by":"crossref","DOI":"10.1109\/ICCVW.2019.00294","article-title":"Fishyscapes: a benchmark for safe semantic segmentation in autonomous driving","author":"Blum","year":"2019"},{"key":"mlstabd614bib324","doi-asserted-by":"publisher","first-page":"1951","DOI":"10.1109\/TITS.2019.2909066","article-title":"Automated evaluation of semantic segmentation robustness for autonomous driving","volume":"21","author":"Zhou","year":"2019","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"mlstabd614bib325","article-title":"Fully-automatic semantic segmentation for food intake tracking in long-term care homes","author":"Pfisterer","year":"2019"},{"key":"mlstabd614bib326","first-page":"1","article-title":"Semantic food segmentation for automatic dietary monitoring","author":"Aslan","year":"2018"},{"key":"mlstabd614bib327","first-page":"1756","article-title":"Automated left atrial segmentation from magnetic resonance image sequences using deep convolutional neural network with autoencoder","author":"Ghosh","year":"2020"},{"key":"mlstabd614bib328","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2020.101715","article-title":"Semantic segmentation of the multiform proximal femur and femoral head bones with the deep convolutional neural networks in low quality mri sections acquired in different mri protocols","volume":"81","author":"Memis","year":"2020","journal-title":"Comput. Med. Imaging Graph."},{"key":"mlstabd614bib329","article-title":"Prostate cancer semantic segmentation by gleason score group in mp-MRI with self attention model on the peripheral zone","author":"Duran","year":"2020"},{"key":"mlstabd614bib330","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12911-019-0988-4","article-title":"A comparison between two semantic deep learning frameworks for the autosomal dominant polycystic kidney disease segmentation based on magnetic resonance images","volume":"19","author":"Bevilacqua","year":"2019","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"mlstabd614bib331","doi-asserted-by":"publisher","first-page":"2379","DOI":"10.1002\/mrm.26841","article-title":"Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal magnetic resonance imaging","volume":"79","author":"Liu","year":"2018","journal-title":"Magn. Reson. Med."},{"key":"mlstabd614bib332","article-title":"Deep semantic segmentation of natural and medical images: a review","author":"Taghanaki","year":"2020","journal-title":"Artif. Intell. Rev."},{"key":"mlstabd614bib333","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101693","article-title":"Embracing imperfect datasets: a review of deep learning solutions for medical image segmentation","volume":"63","author":"Tajbakhsh","year":"2020","journal-title":"Med. Image Anal."},{"key":"mlstabd614bib334","doi-asserted-by":"publisher","first-page":"20508","DOI":"10.2352\/J.ImagingSci.Technol.2020.64.2.020508","article-title":"Medical image segmentation based on U-Net: a review","volume":"64","author":"Du","year":"2020","journal-title":"J. Imaging Sci. Technol."},{"key":"mlstabd614bib335","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105519","article-title":"Hybrid attention for automatic segmentation of whole fetal head in prenatal ultrasound volumes","volume":"194","author":"Yang","year":"2020","journal-title":"Comput. Methods Programs Biomed."},{"key":"mlstabd614bib336","first-page":"1","article-title":"Joint segmentation and landmark localization of fetal femur in ultrasound volumes","author":"Wang","year":"2019"},{"key":"mlstabd614bib337","first-page":"164","article-title":"Multi-task CNN for structural semantic segmentation in 3D fetal brain ultrasound","author":"Venturini","year":"2019"},{"key":"mlstabd614bib338","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1109\/TMI.2018.2858779","article-title":"Towards automated semantic segmentation in prenatal volumetric ultrasound","volume":"38","author":"Yang","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstabd614bib339","first-page":"192","article-title":"StandardGAN: multi-source domain adaptation for semantic segmentation of very high resolution satellite images by data standardization","author":"Tasar","year":"2020"},{"key":"mlstabd614bib340","first-page":"79","article-title":"Deep learning based semantic segmentation applied to satellite image","author":"Barthakur","year":"2020"},{"key":"mlstabd614bib341","doi-asserted-by":"publisher","first-page":"55609","DOI":"10.1109\/ACCESS.2019.2913442","article-title":"Towards accurate high resolution satellite image semantic segmentation","volume":"7","author":"Wu","year":"2019","journal-title":"IEEE Access"},{"key":"mlstabd614bib342","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.isprsjprs.2019.02.006","article-title":"Semantic segmentation of slums in satellite images using transfer learning on fully convolutional neural networks","volume":"150","author":"Wurm","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"mlstabd614bib343","first-page":"182","article-title":"D-LinkNet: linknet with pretrained encoder and dilated convolution for high resolution satellite imagery road extraction","author":"Zhou","year":"2018"},{"key":"mlstabd614bib344","article-title":"Deep multi-class segmentation without ground-truth labels","author":"Joyce","year":"2018"},{"key":"mlstabd614bib345","first-page":"4253","article-title":"Single-stage semantic segmentation from image labels","author":"Araslanov","year":"2020"},{"key":"mlstabd614bib346","article-title":"Exploiting confident information for weakly supervised prostate segmentation based on image-level labels","volume":"vol 11315","author":"Chen","year":"2020"},{"key":"mlstabd614bib347","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1109\/TIP.2019.2926748","article-title":"Coarse-to-fine semantic segmentation from image-level labels","volume":"29","author":"Jing","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"mlstabd614bib348","first-page":"5038","article-title":"Exploiting saliency for object segmentation from image level labels","author":"Oh","year":"2017"},{"key":"mlstabd614bib349","article-title":"Exit wavefunction reconstruction from single transmission electron micrographs with deep learning","author":"Ede","year":"2020"},{"key":"mlstabd614bib350","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.1119\/1.2757621","article-title":"Young\u2019s double-slit interference experiment with electrons","volume":"75","author":"Frabboni","year":"2007","journal-title":"Am. J. Phys."},{"key":"mlstabd614bib351","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.1119\/1.19045","article-title":"An experiment on electron wave-particle duality including a planck constant measurement","volume":"66","author":"Matteucci","year":"1998","journal-title":"Am. J. Phys."},{"key":"mlstabd614bib352","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1017\/S1431927602020147","article-title":"Tutorial on off-axis electron holography","volume":"8","author":"Lehmann","year":"2002","journal-title":"Microsc. Microanal."},{"key":"mlstabd614bib353","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1103\/RevModPhys.59.639","article-title":"Applications of electron holography","volume":"59","author":"Tonomura","year":"1987","journal-title":"Rev. Mod. Phys."},{"key":"mlstabd614bib354","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1107\/S0108767300000040","article-title":"Reconstruction of the projected crystal potential in transmission electron microscopy by means of a maximum-likelihood refinement algorithm","volume":"56","author":"Lentzen","year":"2000","journal-title":"Acta Crystallogr. A"},{"key":"mlstabd614bib355","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.ultramic.2018.12.017","article-title":"Measuring the mean inner potential of Al2O3 sapphire using off-axis electron holography","volume":"198","author":"Auslender","year":"2019","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib356","doi-asserted-by":"publisher","first-page":"2319","DOI":"10.1103\/PhysRevLett.67.2319","article-title":"Correction of aberrations of an electron microscope by means of electron holography","volume":"67","author":"Fu","year":"1991","journal-title":"Phys. Rev. Lett."},{"key":"mlstabd614bib357","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1016\/0304-3991(94)90040-X","article-title":"Absolute measurement of normalized thickness, t \u03bb i , from off-axis electron holography","volume":"53","author":"McCartney","year":"1994","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib358","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1038\/nnano.2014.52","article-title":"Observation of the magnetic flux and three-dimensional structure of skyrmion lattices by electron holography","volume":"9","author":"Park","year":"2014","journal-title":"Nat. Nanotechnol."},{"key":"mlstabd614bib359","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1002\/jemt.20098","article-title":"Off-axis electron holography of magnetic nanowires and chains, rings and planar arrays of magnetic nanoparticles","volume":"64","author":"Dunin-Borkowski","year":"2004","journal-title":"Microsc. Res. Tech."},{"key":"mlstabd614bib360","first-page":"105","article-title":"Fundamentals of focal series inline electron holography","volume":"vol 197","author":"Lubk","year":"2016"},{"key":"mlstabd614bib361","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.micron.2013.10.009","article-title":"Towards full-resolution inline electron holography","volume":"63","author":"Koch","year":"2014","journal-title":"Micron"},{"key":"mlstabd614bib362","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.ultramic.2013.04.012","article-title":"Recording low and high spatial frequencies in exit wave reconstructions","volume":"133","author":"Haigh","year":"2013","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib363","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1016\/j.ultramic.2009.11.022","article-title":"Off-Axis and inline electron holography: a quantitative comparison","volume":"110","author":"Koch","year":"2010","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib364","first-page":"295","article-title":"Object wavefunction reconstruction in high resolution electron microscopy","volume":"vol 3","author":"Van Dyck","year":"1994"},{"key":"mlstabd614bib365","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/srep07020","article-title":"Hybridization approach to in-line and off-axis (electron) holography for superior resolution and phase sensitivity","volume":"4","author":"Ozsoy-Keskinbora","year":"2014","journal-title":"Sci. Rep."},{"key":"mlstabd614bib366","doi-asserted-by":"publisher","DOI":"10.1038\/lsa.2017.141","article-title":"Phase recovery and holographic image reconstruction using deep learning in neural networks","volume":"7","author":"Rivenson","year":"2018","journal-title":"Light: Sci. Appl."},{"key":"mlstabd614bib367","doi-asserted-by":"publisher","first-page":"704","DOI":"10.1364\/OPTICA.5.000704","article-title":"Extended depth-of-field in holographic imaging using deep-learning-based autofocusing and phase recovery","volume":"5","author":"Wu","year":"2018","journal-title":"Optica"},{"key":"mlstabd614bib368","doi-asserted-by":"publisher","first-page":"1117","DOI":"10.1364\/OPTICA.4.001117","article-title":"Lensless computational imaging through deep learning","volume":"4","author":"Sinha","year":"2017","journal-title":"Optica"},{"key":"mlstabd614bib369","article-title":"QuCumber: wavefunction reconstruction with neural networks","author":"Beach","year":"2018"},{"key":"mlstabd614bib370","doi-asserted-by":"publisher","first-page":"2336","DOI":"10.1021\/acs.jpclett.9b03664","article-title":"Quantum chemistry in the age of machine learning","volume":"11","author":"Dral","year":"2020","journal-title":"J. Phys. Chem. Lett."},{"key":"mlstabd614bib371","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.124.113202","article-title":"Deep learning for Feynman\u2019s path integral in strong-field time-dependent dynamics","volume":"124","author":"Liu","year":"2020","journal-title":"Phys. Rev. Lett."},{"key":"mlstabd614bib372","doi-asserted-by":"crossref","DOI":"10.1116\/5.0007529","article-title":"Machine learning meets quantum foundations: a brief survey","author":"Bharti","year":"2020"},{"key":"mlstabd614bib373","doi-asserted-by":"crossref","DOI":"10.1016\/j.softx.2019.100311","article-title":"NetKet: a machine learning toolkit for many-body quantum systems","author":"Carleo","year":"2019"},{"key":"mlstabd614bib374","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-019-12875-2","article-title":"Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctions","volume":"10","author":"Sch\u00fctt","year":"2019","journal-title":"Nat. Commun."},{"key":"mlstabd614bib375","article-title":"Reconstruction of 3-D atomic distortions from electron microscopy with deep learning","author":"Laanait","year":"2019"},{"key":"mlstabd614bib376","doi-asserted-by":"publisher","first-page":"1455","DOI":"10.1016\/j.ultramic.2011.07.005","article-title":"Direct exit-wave reconstruction from a single defocused image","volume":"111","author":"Morgan","year":"2011","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib377","doi-asserted-by":"publisher","first-page":"5114","DOI":"10.1016\/j.optcom.2008.07.006","article-title":"Direct retrieval of a complex wave from its diffraction pattern","volume":"281","author":"Martin","year":"2008","journal-title":"Opt. Commun."},{"key":"mlstabd614bib378","article-title":"Science without publication paywalls a preamble to: coalition s for the realisation of full and immediate open access","author":"Schlitz","year":"2018","journal-title":"Science Europe"},{"key":"mlstabd614bib379","article-title":"\u2018Plan S\u2019 to require full OA, cap APCs, and disallow publication in hybrid journals","author":"","year":"2018"},{"key":"mlstabd614bib380","article-title":"Plan S: making full and immediate open access a reality","author":"cOAlition","year":"2020"},{"key":"mlstabd614bib381","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/s10869-018-9547-8","article-title":"Answers to 18 questions about open science practices","volume":"34","author":"Banks","year":"2019","journal-title":"J. Bus. Psychol."},{"key":"mlstabd614bib382","first-page":"p 320","article-title":"FTDL: an FPGA-tailored architecture for deep learning systems","author":"Shi","year":"2020"},{"key":"mlstabd614bib383","first-page":"471","article-title":"FPGA based deep learning models for object detection and recognition comparison of object detection comparison of object detection models using FPGA","author":"Kaarmukilan","year":"2020"},{"key":"mlstabd614bib384","first-page":"1674","article-title":"An overview of FPGA based deep learning accelerators: challenges and opportunities","author":"Wang","year":"2019"},{"key":"mlstabd614bib385","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3289185","article-title":"[DL] a survey of fpga-based neural network inference accelerators","volume":"12","author":"Guo","year":"2019","journal-title":"ACM Trans. Reconfigurable Technol. Syst."},{"key":"mlstabd614bib386","doi-asserted-by":"publisher","first-page":"e1232","DOI":"10.1002\/widm.1232","article-title":"A survey on graphic processing unit computing for large-scale data mining","volume":"8","author":"Cano","year":"2018","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"mlstabd614bib387","article-title":"Tesla V100 GPU architecture whitepaper","author":"","year":"2017"},{"key":"mlstabd614bib388","author":"Gaster","year":"2013","edition":"2nd edn"},{"key":"mlstabd614bib389","first-page":"65","article-title":"Scaling analysis of specialized tensor processing architectures for deep learning models","author":"Gordienko","year":"2020"},{"key":"mlstabd614bib390","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1109\/MM.2018.032271057","article-title":"Motivation for and evaluation of the first tensor processing unit","volume":"38","author":"Jouppi","year":"2018","journal-title":"IEEE Micro"},{"key":"mlstabd614bib391","first-page":"1","article-title":"In-datacenter performance analysis of a tensor processing unit","author":"Jouppi","year":"2017"},{"key":"mlstabd614bib392","article-title":"MLPerf training benchmark","author":"Mattson","year":"2020"},{"key":"mlstabd614bib393","author":"","year":"2020"},{"key":"mlstabd614bib394","article-title":"Benchmarking TPU, GPU, and CPU platforms for deep learning","author":"Wang","year":"2019"},{"key":"mlstabd614bib395","article-title":"Performance and power evaluation of AI accelerators for training deep learning models","author":"Wang","year":"2019"},{"key":"mlstabd614bib396","doi-asserted-by":"publisher","first-page":"4353","DOI":"10.1007\/s00521-018-3354-z","article-title":"Cpu versus gpu: which can perform matrix computation faster\u2014performance comparison for basic linear algebra subprograms","volume":"31","author":"Li","year":"2019","journal-title":"Neural Comput. Appl."},{"key":"mlstabd614bib397","first-page":"1","article-title":"An in-depth performance characterization of CPU-and GPU-based DNN training on modern architectures","author":"Awan","year":"2017"},{"key":"mlstabd614bib398","first-page":"5","article-title":"Can FPGAs beat GPUs in accelerating next-generation deep neural networks?","author":"Nurvitadhi","year":"2017"},{"key":"mlstabd614bib399","article-title":"Berten digital signal processing","author":"","year":"2016"},{"key":"mlstabd614bib400","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1016\/j.procs.2018.05.096","article-title":"Resource utilization optimization with design alternatives in FPGA based arithmetic logic unit architectures","volume":"132","author":"Nangia","year":"2018","journal-title":"Proc. Comput. Sci."},{"key":"mlstabd614bib401","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5815\/ijieeb.2014.01.01","article-title":"Design of FPGA based 32-bit floating point arithmetic unit and verification of its VHDL code using MATLAB","volume":"6","author":"Grover","year":"2014","journal-title":"Int. J. Inf. Eng. Electron. Bus."},{"key":"mlstabd614bib402","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1007\/s11227-017-2177-5","article-title":"Theoretical peak FLOPS per instruction set: a tutorial","volume":"74","author":"Dolbeau","year":"2018","journal-title":"J. Supercomput."},{"key":"mlstabd614bib403","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P19-1355","article-title":"Energy and policy considerations for deep learning in NLP","author":"Strubell","year":"2019"},{"key":"mlstabd614bib404","first-page":"533","article-title":"Notes on using google colaboratory in AI education","author":"Nelson","year":"2020"},{"key":"mlstabd614bib405","first-page":"59","article-title":"Google colaboratory","author":"Bisong","year":"2019"},{"key":"mlstabd614bib406","author":"","year":"2019"},{"key":"mlstabd614bib407","doi-asserted-by":"publisher","first-page":"61677","DOI":"10.1109\/ACCESS.2018.2874767","article-title":"Performance analysis of google colaboratory as a tool for accelerating deep learning applications","volume":"6","author":"Carneiro","year":"2018","journal-title":"IEEE Access"},{"key":"mlstabd614bib408","author":"","year":"2020"},{"key":"mlstabd614bib409","article-title":"Decoding the relationship between domain structure and functionality in ferroelectrics via hidden latent variables","author":"Kalinin","year":"2020"},{"key":"mlstabd614bib410","article-title":"How to install a new graphics card\u2014from hardware to drivers","author":"Green","year":"2019"},{"key":"mlstabd614bib411","article-title":"How to install a graphics card","author":"Ryan","year":"2017"},{"key":"mlstabd614bib412","article-title":"An utterly simple guide on installing Tensorflow-GPU 2.0 on Windows 10","author":"Radecic","year":"2020"},{"key":"mlstabd614bib413","article-title":"Train neural networks using AMD GPU and Keras","author":"Varile","year":"2019"},{"key":"mlstabd614bib414","article-title":"A full hardware guide to deep learning","author":"","year":"2018"},{"key":"mlstabd614bib415","article-title":"cuDNN: efficient primitives for deep learning","author":"Chetlur","year":"2014"},{"key":"mlstabd614bib416","author":"","year":"2020"},{"key":"mlstabd614bib417","first-page":"240","article-title":"Infrastructures for high-performance computing: cloud infrastructures","author":"Marozzo","year":"2019"},{"key":"mlstabd614bib418","first-page":"413","author":"Joshi","year":"2019"},{"key":"mlstabd614bib419","first-page":"236","article-title":"Deploying an application using google cloud platform","author":"Gupta","year":"2020"},{"key":"mlstabd614bib420","first-page":"685","article-title":"SINGA: a distributed deep learning platform","author":"Ooi","year":"2015"},{"key":"mlstabd614bib421","author":"","year":"2020"},{"key":"mlstabd614bib422","first-page":"50","article-title":"BigDL: a distributed deep learning framework for big data","author":"Dai","year":"2019"},{"key":"mlstabd614bib423","author":"","year":"2020"},{"key":"mlstabd614bib424","first-page":"675","article-title":"Caffe: convolutional architecture for fast feature embedding","author":"Jia","year":"2014"},{"key":"mlstabd614bib425","author":""},{"key":"mlstabd614bib426","author":"","year":"2017"},{"key":"mlstabd614bib427","first-page":"1","article-title":"Chainer: a next-generation open source framework for deep learning","volume":"vol 5","author":"Tokui","year":"2015"},{"key":"mlstabd614bib428","author":"","year":"2020"},{"key":"mlstabd614bib429","article-title":"Deeplearning4j: distributed, open-source deep learning for Java and Scala on Hadoop and Spark","author":"Gibson","year":"2016"},{"key":"mlstabd614bib430","author":"","year":"2020"},{"key":"mlstabd614bib431","first-page":"1755","article-title":"Dlib-ml: a machine learning toolkit","volume":"10","author":"King","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"mlstabd614bib432","author":"","year":"2020"},{"key":"mlstabd614bib433","author":"","year":"2020"},{"key":"mlstabd614bib434","doi-asserted-by":"publisher","first-page":"602","DOI":"10.21105\/joss.00602","article-title":"Flux: elegant machine learning with Julia","volume":"3","author":"Innes","year":"2018","journal-title":"J. Open Source Softw."},{"key":"mlstabd614bib435","author":"","year":"2020"},{"key":"mlstabd614bib436","article-title":"PDF documentation: matlab deep learning toolbox user\u2019s guide","author":"Beale","year":"2020"},{"key":"mlstabd614bib437","author":"","year":"2020"},{"key":"mlstabd614bib438","first-page":"p xi","article-title":"Keynote: the computer science behind the microsoft cognitive toolkit: an open source large-scale deep learning toolkit for windows and linux","author":"Seide","year":"2017"},{"key":"mlstabd614bib439","author":"","year":"2020"},{"key":"mlstabd614bib440","article-title":"MXNet: a flexible and efficient machine learning library for heterogeneous distributed systems","author":"Chen","year":"2015"},{"key":"mlstabd614bib441","author":"","year":"2020"},{"key":"mlstabd614bib442","author":"","year":"2020"},{"key":"mlstabd614bib443","author":"","year":"2020"},{"key":"mlstabd614bib444","first-page":"105","article-title":"PaddlePaddle: an open-source deep learning platform from industrial practice","volume":"1","author":"Ma","year":"2019","journal-title":"Front. Data Comput."},{"key":"mlstabd614bib445","author":"","year":"2020"},{"key":"mlstabd614bib446","first-page":"8024","article-title":"PyTorch: an imperative style, high-performance deep learning library","author":"Paszke","year":"2019"},{"key":"mlstabd614bib447","author":"","year":"2020"},{"key":"mlstabd614bib448","first-page":"265","article-title":"TensorFlow: a system for large-scale machine learning","author":"Abadi","year":"2016"},{"key":"mlstabd614bib449","article-title":"TensorFlow: large-scale machine learning on heterogeneous distributed systems","author":"Abadi","year":"2016"},{"key":"mlstabd614bib450","author":"","year":"2020"},{"key":"mlstabd614bib451","article-title":"Theano: a python framework for fast computation of mathematical expressions","author":"Team","year":"2016"},{"key":"mlstabd614bib452","first-page":"35","author":"Ketkar","year":"2017"},{"key":"mlstabd614bib453","author":"","year":"2020"},{"key":"mlstabd614bib454","article-title":"Torch: a modular machine learning software library","author":"Collobert","year":"2002"},{"key":"mlstabd614bib455","author":"","year":"2020"},{"key":"mlstabd614bib456","author":"","year":"2020"},{"key":"mlstabd614bib457","author":"","year":"2020"},{"key":"mlstabd614bib458","article-title":"The deep learning compiler: a comprehensive survey","author":"Li","year":"2020"},{"key":"mlstabd614bib459","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/s10462-018-09679-z","article-title":"Machine learning and deep learning frameworks and libraries for large-scale data mining: a survey","volume":"52","author":"Nguyen","year":"2019","journal-title":"Artif. Intell. Rev."},{"key":"mlstabd614bib460","first-page":"148","article-title":"Benchmarking contemporary deep learning hardware and frameworks: a survey of qualitative metrics","author":"Dai","year":"2019"},{"key":"mlstabd614bib461","article-title":"Top 10 best deep learning frameworks in 2019","author":"Kharkovyna","year":"2019"},{"key":"mlstabd614bib462","article-title":"A survey on deep learning toolkits and libraries for intelligent user interfaces","author":"Zacharias","year":"2018"},{"key":"mlstabd614bib463","first-page":"1","article-title":"A survey of deep-learning frameworks","author":"Parvat","year":"2017"},{"key":"mlstabd614bib464","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1007\/s10278-017-9965-6","article-title":"Toolkits and libraries for deep learning","volume":"30","author":"Erickson","year":"2017","journal-title":"J. Digit. Imaging"},{"key":"mlstabd614bib465","first-page":"5595","volume":"18","author":"Baydin","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"mlstabd614bib466","first-page":"177","article-title":"Machine learning systems are stuck in a rut","author":"Barham","year":"2019"},{"key":"mlstabd614bib467","first-page":"1","article-title":"Computer vision algorithms acceleration using graphic processors NVIDIA CUDA","author":"Afif","year":"2020"},{"key":"mlstabd614bib468","author":"Cook","year":"2012","edition":"1st edn"},{"key":"mlstabd614bib469","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1145\/1365490.1365500","article-title":"Scalable parallel programming with CUDA","volume":"6","author":"Nickolls","year":"2008","journal-title":"Queue"},{"key":"mlstabd614bib470","doi-asserted-by":"publisher","first-page":"70461","DOI":"10.1109\/ACCESS.2019.2918851","article-title":"Performance evaluation of cudnn convolution algorithms on NVIDIA volta GPUs","volume":"7","author":"Jord\u00e0","year":"2019","journal-title":"IEEE Access"},{"key":"mlstabd614bib471","doi-asserted-by":"publisher","first-page":"2004","DOI":"10.1109\/JPROC.2018.2853600","article-title":"The ongoing evolution of openMP","volume":"106","author":"de Supinski","year":"2018","journal-title":"Proc. IEEE"},{"key":"mlstabd614bib472","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/99.660313","article-title":"OpenMP: an industry standard API for shared-memory programming","volume":"5","author":"Dagum","year":"1998","journal-title":"IEEE Comput. Sci. Eng."},{"key":"mlstabd614bib473","article-title":"The state of machine learning frameworks in 2019","author":"He","year":"2019"},{"key":"mlstabd614bib474","author":"","year":"2020"},{"key":"mlstabd614bib475","author":"","year":"2020"},{"key":"mlstabd614bib476","author":"Chollet","year":"2020"},{"key":"mlstabd614bib477","author":"","year":"2020"},{"key":"mlstabd614bib478","article-title":"Tensor2tensor for neural machine translation","author":"Vaswani","year":"2018"},{"key":"mlstabd614bib479","article-title":"TF.Learn: tensorflow\u2019s high-level module for distributed machine learning","author":"Tang","year":"2016"},{"key":"mlstabd614bib480","article-title":"TFLearn repository","author":"Damien","year":"2019"},{"key":"mlstabd614bib481","author":"","year":"2020"},{"key":"mlstabd614bib482","article-title":"TF-Agents: a library for reinforcement learning in tensorflow","author":"Sergio","year":"2018"},{"key":"mlstabd614bib483","article-title":"Dopamine: a research framework for deep reinforcement learning","author":"Castro","year":"2018"},{"key":"mlstabd614bib484","article-title":"Federated learning: collaborative machine learning without centralized training data","volume":"4","author":"McMahan","year":"2017","journal-title":"Google Research Blog"},{"key":"mlstabd614bib485","author":"","year":"2018"},{"key":"mlstabd614bib486","article-title":"LEAF: a benchmark for federated settings","author":"Caldas","year":"2018"},{"key":"mlstabd614bib487","article-title":"TensorFlow distributions","author":"Dillon","year":"2017"},{"key":"mlstabd614bib488","article-title":"Open sourcing trfl: a library of reinforcement learning building blocks","author":"Hessel","year":"2018"},{"key":"mlstabd614bib489","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"mlstabd614bib490","author":"","year":"2020"},{"key":"mlstabd614bib491","author":"","year":"2020"},{"key":"mlstabd614bib492","author":"","year":"2020"},{"key":"mlstabd614bib493","author":"","year":"2020"},{"key":"mlstabd614bib494","author":"","year":"2020"},{"key":"mlstabd614bib495","author":"","year":"2020"},{"key":"mlstabd614bib496","author":"","year":"2020"},{"key":"mlstabd614bib497","author":"","year":"2020"},{"key":"mlstabd614bib498","author":"Witten","year":"2016"},{"key":"mlstabd614bib499","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1145\/1656274.1656278","article-title":"The WEKA data mining software: an update","volume":"11","author":"Hall","year":"2009","journal-title":"ACM SIGKDD Explorations Newsl."},{"key":"mlstabd614bib500","first-page":"357","article-title":"WEKA: a machine learning workbench","author":"Holmes","year":"1994"},{"key":"mlstabd614bib501","article-title":"ZeroCostDL4Mic: an open platform to simplify access and use of deep-learning in microscopy","author":"Von Chamier","year":"2020"},{"key":"mlstabd614bib502","article-title":"Understanding geometry of encoder\u2013decoder CNNs","author":"Ye","year":"2019"},{"key":"mlstabd614bib503","doi-asserted-by":"publisher","first-page":"991","DOI":"10.1137\/17M1141771","article-title":"Deep convolutional framelets: a general deep learning framework for inverse problems","volume":"11","author":"Ye","year":"2018","journal-title":"SIAM J. Imaging Sci."},{"key":"mlstabd614bib504","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"Sutskever","year":"2014"},{"key":"mlstabd614bib505","author":"","year":"2020"},{"key":"mlstabd614bib506","author":"","year":"2020"},{"key":"mlstabd614bib507","author":"","year":"2020"},{"key":"mlstabd614bib508","article-title":"ONNX: open neural network exchange","author":"Bai","year":"2020"},{"key":"mlstabd614bib509","article-title":"Microsoft and facebook\u2019s open AI ecosystem gains more support","author":"Shah","year":"2017"},{"key":"mlstabd614bib510","article-title":"Microsoft and Facebook create open ecosystem for AI model interoperability","author":"Boyd","year":"2017"},{"key":"mlstabd614bib511","author":"","year":"2020"},{"key":"mlstabd614bib512","article-title":"Introducing tensorflow hub: a library for reusable machine learning modules in tensorflow","author":"Gordon","year":"2018"},{"key":"mlstabd614bib513","author":"","year":"2020"},{"key":"mlstabd614bib514","author":"","year":"2020"},{"key":"mlstabd614bib515","first-page":"1516","article-title":"A survey of recent advances in transfer learning","author":"Liang","year":"2019"},{"key":"mlstabd614bib516","article-title":"A comprehensive survey on transfer learning","author":"Zhuang","year":"2019"},{"key":"mlstabd614bib517","first-page":"270","article-title":"A survey on deep transfer learning","author":"Tan","year":"2018"},{"key":"mlstabd614bib518","article-title":"Transfer learning from pre-trained models","author":"Marcelino","year":"2018"},{"key":"mlstabd614bib519","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/s40537-016-0043-6","article-title":"A survey of transfer learning","volume":"3","author":"Weiss","year":"2016","journal-title":"J. Big data"},{"key":"mlstabd614bib520","first-page":"3320","article-title":"How transferable are features in deep neural networks?","author":"Yosinski","year":"2014"},{"key":"mlstabd614bib521","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/s10458-019-09430-0","article-title":"Agents teaching agents: a survey on inter-agent transfer learning","volume":"34","author":"Da Silva","year":"2020","journal-title":"Auton. Agent. Multi Agent Syst."},{"key":"mlstabd614bib522","first-page":"142","article-title":"Enhanced transfer learning with imagenet trained classification layer","author":"Shermin","year":"2019"},{"key":"mlstabd614bib523","article-title":"Generalization in transfer learning","author":"Ada","year":"2019"},{"key":"mlstabd614bib524","article-title":"Neural network exchange format","author":"","year":"2020"},{"key":"mlstabd614bib525","author":"","year":"2020"},{"key":"mlstabd614bib526","author":"","year":"2020"},{"key":"mlstabd614bib527","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1017\/S1431927619001831","article-title":"USID and pycroscopy\u2014open source frameworks for storing and analyzing imaging and spectroscopy data","volume":"25","author":"Somnath","year":"2019","journal-title":"Microsc. Microanal."},{"key":"mlstabd614bib528","author":"","year":"2020"},{"key":"mlstabd614bib529","author":"","year":"2020"},{"key":"mlstabd614bib530","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1017\/S1431927617001751","article-title":"Electron microscopy (big and small) data analysis with the open source software package hyperspy","volume":"23","author":"de la Pe\u00f1a","year":"2017","journal-title":"Microsc. Microanal."},{"key":"mlstabd614bib531","doi-asserted-by":"publisher","first-page":"57967","DOI":"10.1109\/ACCESS.2020.2982416","article-title":"Recurrent neural networks: an embedded computing perspective","volume":"8","author":"Rezk","year":"2020","journal-title":"IEEE Access"},{"key":"mlstabd614bib532","first-page":"351","article-title":"Recurrent neural networks","author":"Du","year":"2019"},{"key":"mlstabd614bib533","doi-asserted-by":"publisher","first-page":"1235","DOI":"10.1162\/neco_a_01199","article-title":"A review of recurrent neural networks: LSTM cells and network architectures","volume":"31","author":"Yu","year":"2019","journal-title":"Neural Comput."},{"key":"mlstabd614bib534","article-title":"Probabilistic interpretations of recurrent neural networks","author":"Choe","year":"2017"},{"key":"mlstabd614bib535","article-title":"Awesome recurrent neural networks","author":"Choi","year":"2017"},{"key":"mlstabd614bib536","article-title":"A critical review of recurrent neural networks for sequence learning","author":"Lipton","year":"2015"},{"key":"mlstabd614bib537","first-page":"571","article-title":"How to start training: the effect of initialization and architecture","author":"Hanin","year":"2018"},{"key":"mlstabd614bib538","article-title":"Model evaluation, model selection, and algorithm selection in machine learning","author":"Raschka","year":"2018"},{"key":"mlstabd614bib539","first-page":"1251","article-title":"Xception: deep learning with depthwise separable convolutions","author":"Chollet","year":"2017"},{"key":"mlstabd614bib540","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","article-title":"The PASCAL visual object classes challenge: a retrospective","volume":"111","author":"Everingham","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"mlstabd614bib541","article-title":"Accurate, large minibatch SGD: training imagenet in 1 hour","author":"Goyal","year":"2017"},{"key":"mlstabd614bib542","article-title":"Exascale deep learning for scientific inverse problems","author":"Laanait","year":"2019"},{"key":"mlstabd614bib543","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1038\/d41586-018-06201-x","article-title":"Google unveils search engine for open data","volume":"561","author":"Castelvecchi","year":"2018","journal-title":"Nature"},{"key":"mlstabd614bib544","article-title":"Discovering millions of datasets on the web","author":"Noy","year":"2020"},{"key":"mlstabd614bib545","article-title":"Machine learning datasets: a list of the biggest machine learning datasets from across the web","author":"Plesa","year":"2020"},{"key":"mlstabd614bib546","article-title":"UCI machine learning repository","author":"Dua","year":"2020"},{"key":"mlstabd614bib547","author":"","year":"2020"},{"key":"mlstabd614bib548","author":"","year":"2020"},{"key":"mlstabd614bib549","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1145\/2641190.2641198","article-title":"OpenML: networked science in machine learning","volume":"15","author":"Vanschoren","year":"2014","journal-title":"ACM SIGKDD Explorations Newsl."},{"key":"mlstabd614bib550","article-title":"The best public datasets for machine learning and data science towards AI","author":"Stanford","year":"2020"},{"key":"mlstabd614bib551","author":"","year":"2020"},{"key":"mlstabd614bib552","article-title":"Natural language processing datasets","author":"Iderhoff","year":"2020"},{"key":"mlstabd614bib553","author":"","year":"2017"},{"key":"mlstabd614bib554","author":"Hughes","year":"2010"},{"key":"mlstabd614bib555","article-title":"JCGM 100: 2008 evaluation of measurement data\u2014guide to the expression of uncertainty in measurement","author":"","year":"2008"},{"key":"mlstabd614bib556","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1038\/embor.2012.36","article-title":"Replicates and repeats - what is the difference and is it significant? A brief discussion of statistics and experimental design","volume":"13","author":"Vaux","year":"2012","journal-title":"EMBO Rep."},{"key":"mlstabd614bib557","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1080\/00048408112340121","article-title":"On the utility of repeating the \u2018same\u2019 experiment","volume":"59","author":"Urbach","year":"1981","journal-title":"Australas. J. Philos."},{"key":"mlstabd614bib558","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1080\/00048407512341281","article-title":"Popper and \u2018diminishing returns from repeated tests\u2019","volume":"53","author":"Musgrave","year":"1975","journal-title":"Australas. J. Philos."},{"key":"mlstabd614bib559","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1038\/s41586-019-1923-7","article-title":"Improved protein structure prediction using potentials from deep learning","volume":"577","author":"Senior","year":"2020","journal-title":"Nature"},{"key":"mlstabd614bib560","doi-asserted-by":"crossref","DOI":"10.1128\/AEM.02026-19","article-title":"Database mining for novel bacterial \u03b2-etherases, glutathione-dependent lignin-degrading enzymes","volume":"86","author":"Vo\u00df","year":"2020","journal-title":"Appl. Environ. Microbiol."},{"key":"mlstabd614bib561","author":"","year":"2020"},{"key":"mlstabd614bib562","article-title":"The CIFAR-10 dataset","author":"Krizhevsky","year":"2014"},{"key":"mlstabd614bib563","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"mlstabd614bib564","article-title":"MNIST handwritten digit database","author":"LeCun","year":"2010"},{"key":"mlstabd614bib565","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"mlstabd614bib566","author":"","year":"2020"},{"key":"mlstabd614bib567","author":"","year":"2020"},{"key":"mlstabd614bib568","author":"","year":"2020"},{"key":"mlstabd614bib569","author":"","year":"2020"},{"key":"mlstabd614bib570","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0215531","article-title":"ETDB-Caltech: a blockchain-based distributed public database for electron tomography","volume":"14","author":"Ortega","year":"2019","journal-title":"PLoS One"},{"key":"mlstabd614bib571","author":"","year":"2020"},{"key":"mlstabd614bib572","doi-asserted-by":"publisher","first-page":"D396","DOI":"10.1093\/nar\/gkv1126","article-title":"EMDataBank unified data resource for 3DEM","volume":"44","author":"Lawson","year":"2016","journal-title":"Nucleic Acids Res."},{"key":"mlstabd614bib573","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1186\/s12859-015-0580-6","article-title":"Navigating 3D electron microscopy maps with EM-SURFER","volume":"16","author":"Esquivel-Rodr\u00edguez","year":"2015","journal-title":"BMC Bioinform."},{"key":"mlstabd614bib574","doi-asserted-by":"crossref","first-page":"D456","DOI":"10.1093\/nar\/gkq880","article-title":"EMDataBank.org: unified data resource for cryoEM","volume":"39","author":"Lawson","year":"2010","journal-title":"Nucleic Acids Res."},{"key":"mlstabd614bib575","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1016\/j.jsb.2003.09.009","article-title":"EMDep: a web-based system for the deposition and validation of high-resolution electron microscopy macromolecular structural information","volume":"144","author":"Henrick","year":"2003","journal-title":"J. Struct. Biol."},{"key":"mlstabd614bib576","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1016\/S0968-0004(02)02176-X","article-title":"New electron microscopy database and deposition system","volume":"27","author":"Tagari","year":"2002","journal-title":"Trends Biochem. Sci."},{"key":"mlstabd614bib577","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1038\/nmeth.3806","article-title":"EMPIAR: a public archive for raw electron microscopy image data","volume":"13","author":"Iudin","year":"2016","journal-title":"Nat. Methods"},{"key":"mlstabd614bib578","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.172","article-title":"The first annotated set of scanning electron microscopy images for nanoscience","volume":"5","author":"Aversa","year":"2018","journal-title":"Sci. Data"},{"key":"mlstabd614bib579","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2016.41","article-title":"Nanomaterial datasets to advance tomography in scanning transmission electron microscopy","volume":"3","author":"Levin","year":"2016","journal-title":"Sci. Data"},{"key":"mlstabd614bib580","author":"","year":"2020"},{"key":"mlstabd614bib581","author":"","year":"2020"},{"key":"mlstabd614bib582","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1107\/S1600576715021871","article-title":"Specification of the crystallographic information file format, version 2.0","volume":"49","author":"Bernstein","year":"2016","journal-title":"J. Appl. Crystallogr."},{"key":"mlstabd614bib583","doi-asserted-by":"crossref","first-page":"3","DOI":"10.5334\/dsj-2016-003","article-title":"The implementation and evolution of STAR\/CIF ontologies: interoperability and preservation of structured data","volume":"15","author":"Hall","year":"2016","journal-title":"Data Sci. J."},{"key":"mlstabd614bib584","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1107\/S0108768102003464","article-title":"CIF: the computer language of crystallography","volume":"58","author":"Brown","year":"2002","journal-title":"Acta Crystallogr. B"},{"key":"mlstabd614bib585","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1107\/S010876739101067X","article-title":"The crystallographic information file (CIF): a new standard archive file for crystallography","volume":"47","author":"Hall","year":"1991","journal-title":"Acta Crystallogr. A"},{"key":"mlstabd614bib586","doi-asserted-by":"publisher","first-page":"38","DOI":"10.5334\/dsj-2017-038","article-title":"Crystallography and databases","volume":"16","author":"Bruno","year":"2017","journal-title":"Data Sci. J."},{"key":"mlstabd614bib587","author":"","year":"2020"},{"key":"mlstabd614bib588","author":"","year":"2020"},{"key":"mlstabd614bib589","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1186\/s13321-018-0279-6","article-title":"Using SMILES strings for the description of chemical connectivity in the crystallography open database","volume":"10","author":"Quir\u00f3s","year":"2018","journal-title":"J. Cheminf."},{"key":"mlstabd614bib590","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1107\/S1600576715022396","article-title":"COD::CIF::Parser:an error-correcting CIF parser for the Perl language","volume":"49","author":"Merkys","year":"2016","journal-title":"J. Appl. Crystallogr."},{"key":"mlstabd614bib591","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1107\/S1600576714025904","article-title":"Computing stoichiometric molecular composition from crystal structures","volume":"48","author":"Gra\u017eulis","year":"2015","journal-title":"J. Appl. Crystallogr."},{"key":"mlstabd614bib592","doi-asserted-by":"publisher","first-page":"D420","DOI":"10.1093\/nar\/gkr900","article-title":"Crystallography open database (COD): an open-access collection of crystal structures and platform for world-wide collaboration","volume":"40","author":"Gra\u017eulis","year":"2012","journal-title":"Nucleic Acids Res."},{"key":"mlstabd614bib593","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1107\/S0021889809016690","article-title":"Crystallography open database\u2014an open-access collection of crystal structures","volume":"42","author":"Gra\u017eulis","year":"2009","journal-title":"J. Appl. Crystallogr."},{"key":"mlstabd614bib594","first-page":"247","article-title":"The American Mineralogist crystal structure database","volume":"88","author":"Downs","year":"2003","journal-title":"Am. Mineral."},{"key":"mlstabd614bib595","doi-asserted-by":"publisher","first-page":"918","DOI":"10.1107\/S160057671900997X","article-title":"Recent developments in the inorganic crystal structure database: theoretical crystal structure data and related features","volume":"52","author":"Zagorac","year":"2019","journal-title":"J. Appl. Crystallogr."},{"key":"mlstabd614bib596","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1107\/S0108767307038081","article-title":"The introduction of structure types into the inorganic crystal structure database ICSD","volume":"63","author":"Allmann","year":"2007","journal-title":"Acta Crystallogr. A"},{"key":"mlstabd614bib597","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1080\/08893110410001664882","article-title":"The inorganic crystal structure database (ICSD) - present and future","volume":"10","author":"Hellenbrandt","year":"2004","journal-title":"Crystallogr. Rev."},{"key":"mlstabd614bib598","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1107\/S0108768102006948","article-title":"New developments in the inorganic crystal structure database (ICSD): accessibility in support of materials research and design","volume":"58","author":"Belsky","year":"2002","journal-title":"Acta Crystallogr. B"},{"key":"mlstabd614bib599","first-page":"77","article-title":"Crystallographic databases","volume":"360","author":"Bergerhoff","year":"1987","journal-title":"Int. Union Crystallogr."},{"key":"mlstabd614bib600","doi-asserted-by":"publisher","first-page":"273","DOI":"10.6028\/jres.101.028","article-title":"NIST crystallographic databases for research and analysis","volume":"101","author":"Mighell","year":"1996","journal-title":"J. Res. Natl Inst. Stand. Technol."},{"key":"mlstabd614bib601","author":"","year":"2020"},{"key":"mlstabd614bib602","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"mlstabd614bib603","article-title":"YouTube-8M: a large-scale video classification benchmark","author":"Abu-El-Haija","year":"2016"},{"key":"mlstabd614bib604","article-title":"QURATOR: innovative technologies for content and data curation","author":"Rehm","year":"2020"},{"key":"mlstabd614bib605","article-title":"DeepDicomSort: an automatic sorting algorithm for brain magnetic resonance imaging data","author":"van der Voort","year":"2020","journal-title":"Neuroinformatics"},{"key":"mlstabd614bib606","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1016\/j.compbiomed.2019.03.001","article-title":"Medical data quality assessment: on the development of an automated framework for medical data curation","volume":"107","author":"Pezoulas","year":"2019","journal-title":"Comput. Biol. Med."},{"key":"mlstabd614bib607","first-page":"158","article-title":"ADeX: a tool for automatic curation of design decision knowledge for architectural decision recommendations","author":"Bhat","year":"2019"},{"key":"mlstabd614bib608","article-title":"Data curation with deep learning [vision]","author":"Thirumuruganathan","year":"2018"},{"key":"mlstabd614bib609","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1006390","article-title":"Scaling up data curation using deep learning: an application to literature triage in genomic variation resources","volume":"14","author":"Lee","year":"2018","journal-title":"PLoS Comput. Biol."},{"key":"mlstabd614bib610","first-page":"87","author":"Freitas","year":"2016"},{"key":"mlstabd614bib611","author":"","year":"2019"},{"key":"mlstabd614bib612","article-title":"Software heritage: why and how to preserve software source code","author":"Di Cosmo","year":"2017"},{"key":"mlstabd614bib613","author":"","year":"2020"},{"key":"mlstabd614bib614","author":"","year":"2020"},{"key":"mlstabd614bib615","author":"","year":"2020"},{"key":"mlstabd614bib616","author":"","year":"2020"},{"key":"mlstabd614bib617","author":"","year":"2020"},{"key":"mlstabd614bib618","author":"","year":"2020"},{"key":"mlstabd614bib619","author":"","year":"2020"},{"key":"mlstabd614bib620","author":"","year":"2020"},{"key":"mlstabd614bib621","author":"","year":"2020"},{"key":"mlstabd614bib622","author":"","year":"2020"},{"key":"mlstabd614bib623","author":"","year":"2020"},{"key":"mlstabd614bib624","author":"","year":"2020"},{"key":"mlstabd614bib625","first-page":"336","article-title":"Understanding watchers on GitHub","author":"Sheoran","year":"2014"},{"key":"mlstabd614bib626","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/s10664-019-09774-x","article-title":"On the relation between github communication activity and merge conflicts","volume":"25","author":"Vale","year":"2020","journal-title":"Empir. Softw. Eng."},{"key":"mlstabd614bib627","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2019.2918536","article-title":"A large scale study of long-time contributor prediction for github projects","author":"Bao","year":"2019","journal-title":"IEEE Trans. Softw. Eng."},{"key":"mlstabd614bib628","first-page":"286","article-title":"Do as I do, not as I say: do contribution guidelines match the GitHub contribution process?","author":"Elazhary","year":"2019"},{"key":"mlstabd614bib629","first-page":"112","article-title":"More common than tou think: an in-depth study of casual contributors","volume":"vol 1","author":"Pinto","year":"2016"},{"key":"mlstabd614bib630","first-page":"694","article-title":"How GitHub contributing.md contributes to contributors","volume":"vol 1","author":"Kobayakawa","year":"2017"},{"key":"mlstabd614bib631","doi-asserted-by":"publisher","first-page":"58930","DOI":"10.1109\/ACCESS.2019.2915247","article-title":"Studying in the \u2018bazaar\u2019: an exploratory study of crowdsourced learning in GitHub","volume":"7","author":"Lu","year":"2019","journal-title":"IEEE Access"},{"key":"mlstabd614bib632","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3359224","article-title":"The signals that potential contributors look for when choosing open-source projects","volume":"3","author":"Qiu","year":"2019","journal-title":"Proc. ACM Hum.-Comput. Interact."},{"key":"mlstabd614bib633","doi-asserted-by":"publisher","first-page":"274","DOI":"10.17706\/jsw.12.4.274-291","article-title":"Open source software hosting platforms: a collaborative perspective\u2019s review","volume":"12","author":"Alamer","year":"2017","journal-title":"J. Softw."},{"key":"mlstabd614bib634","article-title":"Comparison of source-code-hosting facilities\u2014wikipedia, the free encyclopedia","author":"","year":"2020"},{"key":"mlstabd614bib635","author":"","year":"2020"},{"key":"mlstabd614bib636","author":"","year":"2020"},{"key":"mlstabd614bib637","author":"","year":"2020"},{"key":"mlstabd614bib638","author":"Haider","year":"2019"},{"key":"mlstabd614bib639","first-page":"505","article-title":"Measuring the importance of user-generated content to search engines","volume":"vol 13","author":"Vincent","year":"2019"},{"key":"mlstabd614bib640","first-page":"99","article-title":"The role and importance of search engine and search engine optimization","volume":"2","author":"Jain","year":"2013","journal-title":"Int. J. Emerg. Trends Technol. Comput. Sci."},{"key":"mlstabd614bib641","first-page":"107","article-title":"The anatomy of a large-scale hypertextual web search engine","volume":"30","author":"Brin","year":"1998","journal-title":"Comput. Netw."},{"key":"mlstabd614bib642","first-page":"12","article-title":"The effect of content-equivalent near-duplicates on the evaluation of search engines","author":"Fr\u00f6be","year":"2020"},{"key":"mlstabd614bib643","article-title":"The impact of google on discovering scholarly information: managing stm publishers\u2019 visibility in google","author":"Kostagiolas","year":"2020"},{"key":"mlstabd614bib644","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1108\/DTA-05-2019-0083","article-title":"Retrieval performance of google, yahoo and bing for navigational queries in the field of \u2018life science and biomedicine","volume":"54","author":"Gul","year":"2020","journal-title":"Data Technol. Appl."},{"key":"mlstabd614bib645","first-page":"117","article-title":"Retrieval performance of select search engines in the field of physical sciences","author":"Shafi","year":"2019"},{"key":"mlstabd614bib646","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/1369118X.2020.1776367","article-title":"Seek and you shall find? A content analysis on the diversity of five search engines\u2019 results on political queries","author":"Steiner","year":"2020","journal-title":"Inf. Commun. Soc."},{"key":"mlstabd614bib647","first-page":"n1","article-title":"Evaluating the effectiveness of web search engines on results diversification","volume":"24","author":"Wu","year":"2019","journal-title":"Inf. Res."},{"key":"mlstabd614bib648","article-title":"Evaluation of search engines using advanced search: comparative analysis of yahoo and bing","author":"Rahim","year":"2019","journal-title":"Libr. Philos. Pract."},{"key":"mlstabd614bib649","doi-asserted-by":"crossref","DOI":"10.1108\/LHT-11-2019-0229","article-title":"Evaluating the effectiveness of google, parsijoo, rismoon, and yooz to retrieve Persian documents","author":"Tazehkandi","year":"2020"},{"key":"mlstabd614bib650","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/s11192-018-2958-5","article-title":"Google scholar to overshadow them all? Comparing the sizes of 12 academic search engines and bibliographic databases","volume":"118","author":"Gusenbauer","year":"2019","journal-title":"Scientometrics"},{"key":"mlstabd614bib651","doi-asserted-by":"publisher","first-page":"23","DOI":"10.3389\/frma.2018.00023","article-title":"Dimensions: building context for search and evaluation","volume":"3","author":"Hook","year":"2018","journal-title":"Front. Res. Metrics Anal."},{"key":"mlstabd614bib652","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.acalib.2016.11.003","article-title":"Will web search engines replace bibliographic databases in the systematic identification of research?","volume":"43","author":"Bates","year":"2017","journal-title":"J. Acad. Librariansh."},{"key":"mlstabd614bib653","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1002\/mas.21543","article-title":"Anatomy and evolution of database search engines\u2014a central component of mass spectrometry based proteomic workflows","volume":"39","author":"Verheggen","year":"2020","journal-title":"Mass Spectrom. Rev."},{"key":"mlstabd614bib654","first-page":"2145","article-title":"Deep job understanding at linkedin","author":"Li","year":"2020"},{"key":"mlstabd614bib655","article-title":"Study of the usability of linkedin: a social media platform meant to connect employers and employees","author":"Agazzi","year":"2020"},{"key":"mlstabd614bib656","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1002\/leap.1112","article-title":"New web services that help authors choose journals","volume":"30","author":"Forrester","year":"2017","journal-title":"Learn. Publ."},{"key":"mlstabd614bib657","first-page":"1","article-title":"Patent prior art search using deep learning language model","author":"Kang","year":"2020"},{"key":"mlstabd614bib658","first-page":"548","article-title":"Prior art search using multi-modal embedding of patent documents","author":"Kang","year":"2020"},{"key":"mlstabd614bib659","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1007\/s10115-018-1322-7","article-title":"Patent retrieval: a literature review","volume":"61","author":"Shalaby","year":"2019","journal-title":"Knowl. Inf. Syst."},{"key":"mlstabd614bib660","doi-asserted-by":"publisher","first-page":"1","DOI":"10.17485\/ijst\/2017\/v10i37\/116435","article-title":"A literature review on patent information retrieval techniques","volume":"10","author":"Khode","year":"2017","journal-title":"Indian J. Sci. Technol."},{"key":"mlstabd614bib661","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1016\/j.jnca.2019.01.029","article-title":"Academic social networks: modeling, analysis, mining and applications","volume":"132","author":"Kong","year":"2019","journal-title":"J. Netw. Comput. Appl."},{"key":"mlstabd614bib662","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbusres.2019.11.065","article-title":"Global social networking sites and global identity: a three-country study","author":"Makri","year":"2019","journal-title":"J. Bus. Res."},{"key":"mlstabd614bib663","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.1287\/mnsc.2018.3269","article-title":"An experiment in hiring discrimination via online social networks","volume":"66","author":"Acquisti","year":"2020","journal-title":"Manage. Sci."},{"key":"mlstabd614bib664","first-page":"559","article-title":"The case for voter-centered audits of search engines during political elections","author":"Mustafaraj","year":"2020"},{"key":"mlstabd614bib665","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1007\/s10791-018-9341-2","article-title":"Search bias quantification: investigating political bias in social media and web search","volume":"22","author":"Kulshrestha","year":"2019","journal-title":"Inf. Retr. J."},{"key":"mlstabd614bib666","first-page":"824","article-title":"Beyond the bubble: assessing the diversity of political search results","volume":"7","author":"Puschmann","year":"2019","journal-title":"Digit. J."},{"key":"mlstabd614bib667","article-title":"2020 google search survey: how much do users trust their search results?","author":"Ray","year":"2020"},{"key":"mlstabd614bib668","first-page":"75","author":"Johnson","year":"2019"},{"key":"mlstabd614bib669","first-page":"1","article-title":"Teaching and learning without a textbook: undergraduate student perceptions of open educational resources","volume":"20","author":"Lin","year":"2019","journal-title":"Int. Rev. Res. Open Distrib. Learn."},{"key":"mlstabd614bib670","author":"","year":"2020"},{"key":"mlstabd614bib671","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1007\/s10664-018-9634-5","article-title":"How do developers utilize source code from stack overflow?","volume":"24","author":"Wu","year":"2019","journal-title":"Empir. Softw. Eng."},{"key":"mlstabd614bib672","article-title":"Reading answers on stack overflow: not enough!","author":"Zhang","year":"2019","journal-title":"IEEE Trans. Softw. Eng."},{"key":"mlstabd614bib673","first-page":"104","article-title":"An empirical study of common challenges in developing deep learning applications","author":"Zhang","year":"2019"},{"key":"mlstabd614bib674","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2019.2900307","article-title":"Toxic code snippets on stack overflow","author":"Ragkhitwetsagul","year":"2019","journal-title":"IEEE Trans. Softw. Eng."},{"key":"mlstabd614bib675","first-page":"886","article-title":"Are code examples on an online Q and A forum reliable?: a study of API misuse on stack overflow","author":"Zhang","year":"2018"},{"key":"mlstabd614bib676","author":"","year":"2020"},{"key":"mlstabd614bib677","author":"","year":"2020"},{"key":"mlstabd614bib678","author":"","year":"2020"},{"key":"mlstabd614bib679","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1016\/j.ultramic.2005.02.003","article-title":"Scripting-customised microscopy tools for digital micrograph","volume":"103","author":"Mitchell","year":"2005","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib680","author":"","year":"2020"},{"key":"mlstabd614bib681","author":"","year":"2020"},{"key":"mlstabd614bib682","first-page":"147","article-title":"How to search the internet archive without indexing it","author":"Kanhabua","year":"2016"},{"key":"mlstabd614bib683","author":"","year":"2020"},{"key":"mlstabd614bib684","article-title":"The wayback machine: notes on a re-enchantment","author":"Bowyer","year":"2020","journal-title":"Arch. Sci."},{"key":"mlstabd614bib685","first-page":"15","article-title":"Web archiving at the library of congress","volume":"31","author":"Grotke","year":"2011","journal-title":"Comput. Libr."},{"key":"mlstabd614bib686","author":"","year":"2020"},{"key":"mlstabd614bib687","article-title":"My 10 favorite resources for learning data science online","author":"Lewinson","year":"2020"},{"key":"mlstabd614bib688","article-title":"Handpicked resources for learning deep learning in 2020","author":"Chadha","year":"2020"},{"key":"mlstabd614bib689","article-title":"Here are my top resources to learn deep learning","author":"Besbes","year":"2020"},{"key":"mlstabd614bib690","doi-asserted-by":"crossref","DOI":"10.1126\/science.359.6377.725","article-title":"Artificial intelligence faces reproducibility crisis","author":"Hutson","year":"2018"},{"key":"mlstabd614bib691","first-page":"353","article-title":"Reproducibility crisis?","volume":"533","author":"Baker","year":"2016","journal-title":"Nature"},{"key":"mlstabd614bib692","article-title":"DLPaper2Code: auto-generation of code from deep learning research papers","author":"Sethi","year":"2017"},{"key":"mlstabd614bib693","author":"","year":"2018"},{"key":"mlstabd614bib694","doi-asserted-by":"publisher","DOI":"10.1093\/femsle\/fny204","article-title":"The state of the art in peer review","volume":"365","author":"Tennant","year":"2018","journal-title":"FEMS Microbiol. Lett."},{"key":"mlstabd614bib695","doi-asserted-by":"publisher","first-page":"169","DOI":"10.3389\/fnins.2015.00169","article-title":"Emerging trends in peer review\u2014a survey","volume":"9","author":"Walker","year":"2015","journal-title":"Front. Neurosci."},{"key":"mlstabd614bib696","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-018-06602-y","article-title":"Peer reviewers unmasked: largest global survey reveals trends","author":"Vesper","year":"2018","journal-title":"Nature"},{"key":"mlstabd614bib697","doi-asserted-by":"publisher","first-page":"19024","DOI":"10.1109\/ACCESS.2019.2896978","article-title":"On performance of peer review for academic journals: analysis based on distributed parallel system","volume":"7","author":"Tan","year":"2019","journal-title":"IEEE Access"},{"key":"mlstabd614bib698","article-title":"Scientific journals still matter in the era of academic search engines and preprint archives","volume":"71","author":"Kim","year":"2019","journal-title":"J. Assoc. Inf. Sci. Technol."},{"key":"mlstabd614bib699","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1308\/003588414X14055925061397","article-title":"What are journals for?","volume":"97","author":"Rallison","year":"2015","journal-title":"Ann. R. Coll. Surg. Engl."},{"key":"mlstabd614bib700","doi-asserted-by":"publisher","first-page":"2215","DOI":"10.1002\/asi.23329","article-title":"Growth rates of modern science: a bibliometric analysis based on the number of publications and cited references","volume":"66","author":"Bornmann","year":"2015","journal-title":"J. Assoc. Inf. Sci. Technol."},{"key":"mlstabd614bib701","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1136\/jim-2019-001009","article-title":"Journal impact factor: a bumpy ride in an open space","volume":"68","author":"Kaldas","year":"2020","journal-title":"J. Investigative Med."},{"key":"mlstabd614bib702","doi-asserted-by":"publisher","first-page":"1","DOI":"10.17275\/per.20.26.7.2","article-title":"Building journal impact factor quartile into the assessment of academic performance: a case study","volume":"7","author":"Orbay","year":"2020","journal-title":"Participatory Educ. Res."},{"key":"mlstabd614bib703","doi-asserted-by":"publisher","first-page":"1697","DOI":"10.1007\/s11192-019-03338-y","article-title":"Should highly cited items be excluded in impact factor calculation? The effect of review articles on journal impact factor","volume":"122","author":"Lei","year":"2020","journal-title":"Scientometrics"},{"key":"mlstabd614bib704","author":"","year":"2019"},{"key":"mlstabd614bib705","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1080\/02763869.2020.1704597","article-title":"Rise of the rxivs: how preprint servers are changing the publishing process","volume":"39","author":"Hoy","year":"2020","journal-title":"Med. Ref. Serv. Q."},{"key":"mlstabd614bib706","article-title":"In praise of preprints","volume":"5","author":"Fry","year":"2019","journal-title":"Microb. Genom."},{"key":"mlstabd614bib707","first-page":"7","article-title":"Preprints and preprint servers as academic communication tools","volume":"30","author":"Rodr\u00edguez","year":"2019","journal-title":"Revista Cubana de Informaci\u00f3n en Ciencias de la Salud"},{"key":"mlstabd614bib708","author":"","year":"2020"},{"key":"mlstabd614bib709","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1038\/476145a","article-title":"ArXiv at 20","volume":"476","author":"Ginsparg","year":"2011","journal-title":"Nature"},{"key":"mlstabd614bib710","first-page":"618","article-title":"The Relationship between biorxiv preprints, citations and altmetrics","volume":"1","author":"Fraser","year":"2020","journal-title":"Quant. Sci. Stud."},{"key":"mlstabd614bib711","doi-asserted-by":"crossref","first-page":"1403","DOI":"10.1007\/s11192-020-03612-4","article-title":"The impact of preprints in library and information science: an analysis of citations, usage and social attention indicators","volume":"125","author":"Wang","year":"2020","journal-title":"Scientometrics"},{"key":"mlstabd614bib712","first-page":"101","article-title":"Open access to scholarly communications: advantages, policy and advocacy","author":"Furnival","year":"2020"},{"key":"mlstabd614bib713","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.52646","article-title":"Meta-research: releasing a preprint is associated with more attention and citations for the peer-reviewed article","volume":"8","author":"Fu","year":"2019","journal-title":"Elife"},{"key":"mlstabd614bib714","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0148257","article-title":"Open access meets discoverability: citations to articles posted to academia.edu","volume":"11","author":"Niyazov","year":"2016","journal-title":"PLoS One"},{"key":"mlstabd614bib715","article-title":"State of open access penetration in universities worldwide","author":"Robinson-Garcia","year":"2020"},{"key":"mlstabd614bib716","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1162\/qss_a_00016","article-title":"The pricing of open access journals: diverse niches and sources of value in academic publishing","volume":"1","author":"Siler","year":"2020","journal-title":"Quant. Sci. Stud."},{"key":"mlstabd614bib717","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1002\/leap.1219","article-title":"Is open access affordable? Why current models do not work and why we need internet-era transformation of scholarly communications","volume":"32","author":"Green","year":"2019","journal-title":"Learn. Publ."},{"key":"mlstabd614bib718","doi-asserted-by":"publisher","first-page":"1371","DOI":"10.1007\/s11192-018-2716-8","article-title":"The influence of journal publisher characteristics on open access policy trends","volume":"115","author":"Gadd","year":"2018","journal-title":"Scientometrics"},{"key":"mlstabd614bib719","author":"","year":"2020"},{"key":"mlstabd614bib720","first-page":"117","article-title":"Open journals that piggyback on arXiv gather momentum","volume":"530","author":"Gibney","year":"2016","journal-title":"Nature News"},{"key":"mlstabd614bib721","doi-asserted-by":"publisher","first-page":"59","DOI":"10.3390\/publications7030059","article-title":"Which are the tools available for scholars? A review of assisting software for authors during peer reviewing process","volume":"7","author":"Mart\u00ednez-L\u00f3pez","year":"2019","journal-title":"Publications"},{"key":"mlstabd614bib722","author":"","year":"2020"},{"key":"mlstabd614bib723","author":"","year":"2020"},{"key":"mlstabd614bib724","first-page":"8","article-title":"Introduction to LATEX and to some of its tools","volume":"28","author":"Pignalberi","year":"2019","journal-title":"ArsTEXnica"},{"key":"mlstabd614bib725","article-title":"Pimp your thesis: a minimal introduction to LATEX","author":"Bransen","year":"2018"},{"key":"mlstabd614bib726","author":"Lamport","year":"1994"},{"key":"mlstabd614bib727","doi-asserted-by":"crossref","DOI":"10.1038\/d41586-019-01796-1","article-title":"Craft beautiful equations in word with LaTeX","author":"Matthews","year":"2019"},{"key":"mlstabd614bib728","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0115069","article-title":"An efficiency comparison of document preparation systems used in academic research and development","volume":"9","author":"Knauff","year":"2014","journal-title":"PLoS One"},{"key":"mlstabd614bib729","author":"","year":"2017"},{"key":"mlstabd614bib730","article-title":"The LaTeX fetish (or: don\u2019t write in LaTeX! It\u2019s just for typesetting)","author":"Allington","year":"2016"},{"key":"mlstabd614bib731","author":"","year":"2020"},{"key":"mlstabd614bib732","doi-asserted-by":"publisher","first-page":"512","DOI":"10.3390\/polym12030512","article-title":"Microscopic techniques for the analysis of micro and nanostructures of biopolymers and their derivatives","volume":"12","author":"Venkateshaiah","year":"2020","journal-title":"Polymers"},{"key":"mlstabd614bib733","doi-asserted-by":"publisher","first-page":"33","DOI":"10.3390\/membranes10020033","article-title":"Microscopy and spectroscopy techniques for characterization of polymeric membranes","volume":"10","author":"Alqaheem","year":"2020","journal-title":"Membranes"},{"key":"mlstabd614bib734","author":"Morrison","year":"2019"},{"key":"mlstabd614bib735","doi-asserted-by":"publisher","first-page":"86","DOI":"10.2174\/1874440001812010086","article-title":"Review of progress in atomic force microscopy","volume":"12","author":"Maghsoudy-Louyeh","year":"2018","journal-title":"Open Neuroimaging J."},{"key":"mlstabd614bib736","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1063\/1.881238","article-title":"Atomic force microscopy","volume":"43","author":"Rugar","year":"1990","journal-title":"Phys. Today"},{"key":"mlstabd614bib737","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s42005-020-0317-3","article-title":"Artificial-intelligence-driven scanning probe microscopy","volume":"3","author":"Krull","year":"2020","journal-title":"Commun. Phys."},{"key":"mlstabd614bib738","first-page":"73","author":"Dutta","year":"2017"},{"key":"mlstabd614bib739","volume":"vol 171","author":"Griffiths","year":"2007"},{"key":"mlstabd614bib740","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1146\/annurev-matsci-091019-011049","article-title":"Recent advances in solid-state nuclear magnetic resonance techniques for materials research","volume":"50","author":"Chien","year":"2020","journal-title":"Ann. Rev. Mater. Res."},{"key":"mlstabd614bib741","author":"Lambert","year":"2019"},{"key":"mlstabd614bib742","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/j.ab.2016.05.006","article-title":"Introduction to nuclear magnetic resonance","volume":"529","author":"Mlyn\u00e1rik","year":"2017","journal-title":"Anal. Biochem."},{"key":"mlstabd614bib743","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1103\/PhysRev.53.318","article-title":"A new method of measuring nuclear magnetic moment","volume":"53","author":"Rabi","year":"1938","journal-title":"Phys. Rev."},{"key":"mlstabd614bib744","author":"Smith","year":"2019"},{"key":"mlstabd614bib745","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s11671-019-3039-2","article-title":"Raman techniques: Fundamentals and frontiers","volume":"14","author":"Jones","year":"2019","journal-title":"Nanoscale Res. Lett."},{"key":"mlstabd614bib746","doi-asserted-by":"publisher","first-page":"3289","DOI":"10.1007\/s00170-019-04508-1","article-title":"A review of basic crystallography and x-ray diffraction applications","volume":"105","author":"Ameh","year":"2019","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"mlstabd614bib747","first-page":"2454","article-title":"Raman spectroscopy, review","volume":"6","author":"Rostron","year":"2016","journal-title":"Int. J. Eng. Tech. Res."},{"key":"mlstabd614bib748","doi-asserted-by":"publisher","first-page":"6435","DOI":"10.1039\/C5NR07205K","article-title":"Review on the raman spectroscopy of different types of layered materials","volume":"8","author":"Zhang","year":"2016","journal-title":"Nanoscale"},{"key":"mlstabd614bib749","first-page":"81","article-title":"X-ray diffraction (XRD) techniques for materials characterization","author":"Epp","year":"2016"},{"key":"mlstabd614bib750","doi-asserted-by":"publisher","first-page":"5844","DOI":"10.1073\/pnas.0710575105","article-title":"Noninvasive molecular imaging of small living subjects using raman spectroscopy","volume":"105","author":"Keren","year":"2008","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstabd614bib751","doi-asserted-by":"publisher","first-page":"1255","DOI":"10.1002\/cjce.23747","article-title":"Experimental methods in chemical engineering: x-ray diffraction spectroscopy\u2014XRD","volume":"98","author":"Khan","year":"2020","journal-title":"Can. J. Chem. Eng."},{"key":"mlstabd614bib752","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1107\/S160057751601612X","article-title":"Dynamic x-ray diffraction sampling for protein crystal positioning","volume":"24","author":"Scarborough","year":"2017","journal-title":"J. Synchrotron Radiat."},{"key":"mlstabd614bib753","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.sab.2019.02.003","article-title":"Energy dispersive inelastic x-ray scattering spectroscopy\u2014a review","volume":"154","author":"Leani","year":"2019","journal-title":"Spectrochim. Acta B"},{"key":"mlstabd614bib754","doi-asserted-by":"publisher","first-page":"1704","DOI":"10.1039\/D0JA90051F","article-title":"2020 Atomic spectrometry update\u2014a review of advances in x-ray fluorescence spectrometry and its special applications","volume":"35","author":"Vanhoof","year":"2020","journal-title":"J. Anal. At. Spectrom."},{"key":"mlstabd614bib755","first-page":"1","article-title":"X-ray fluorescence spectrometry (XRF)","author":"Shackley","year":"2018","journal-title":"Encyclopedia Archaeolog. Sci."},{"key":"mlstabd614bib756","doi-asserted-by":"publisher","DOI":"10.1016\/j.pmatsci.2019.100591","article-title":"X-ray photoelectron spectroscopy: towards reliable binding energy referencing","volume":"107","author":"Greczynski","year":"2020","journal-title":"Prog. Mater. Sci."},{"key":"mlstabd614bib757","doi-asserted-by":"publisher","DOI":"10.1116\/1.5065501","article-title":"Practical guides for x-ray photoelectron spectroscopy: first steps in planning, conducting and reporting XPS measurements","volume":"37","author":"Baer","year":"2019","journal-title":"J. Vac. Sci. Technol. A"},{"key":"mlstabd614bib758","article-title":"Relative merits and limiting factors for x-ray and electron microscopy of thick, hydrated organic materials (revised)","author":"Du","year":"2020"},{"key":"mlstabd614bib759","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1002\/jemt.1070200403","article-title":"Technique of reflection electron microscopy","volume":"20","author":"Hsu","year":"1992","journal-title":"Microsc. Res. Tech."},{"key":"mlstabd614bib760","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1107\/S0021889887086916","article-title":"Reflection electron microscopy","volume":"20","author":"Yagi","year":"1987","journal-title":"J. Appl. Crystallogr."},{"key":"mlstabd614bib761","first-page":"7","article-title":"Scanning electron microscopy (SEM): a review","author":"Mohammed","year":"2018"},{"key":"mlstabd614bib762","author":"Goldstein","year":"2017"},{"key":"mlstabd614bib763","author":"Keyse","year":"2018"},{"key":"mlstabd614bib764","author":"Pennycook","year":"2011"},{"key":"mlstabd614bib765","first-page":"p 2","author":"Sutter","year":"2019"},{"key":"mlstabd614bib766","doi-asserted-by":"publisher","DOI":"10.1063\/1.5042346","article-title":"Invited review article: multi-tip scanning tunneling microscopy: experimental techniques and data analysis","volume":"89","author":"Voigtl\u00e4nder","year":"2018","journal-title":"Rev. Sci. Instrum."},{"key":"mlstabd614bib767","author":"Carter","year":"2016"},{"key":"mlstabd614bib768","first-page":"145","author":"Tang","year":"2017"},{"key":"mlstabd614bib769","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.abb.2014.11.011","article-title":"Transmission electron microscopy in molecular structural biology: a historical survey","volume":"581","author":"Harris","year":"2015","journal-title":"Arch. Biochem. Biophys."},{"key":"mlstabd614bib770","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1162\/qss_a_00020","article-title":"Dimensions: bringing down barriers between scientometricians and data","volume":"1","author":"Herzog","year":"2020","journal-title":"Quant. Sci. Stud."},{"key":"mlstabd614bib771","article-title":"A guide to the dimensions data approach","author":"Bode","year":"2018","journal-title":"Digit. Sci."},{"key":"mlstabd614bib772","article-title":"Dimensions-a collaborative approach to enhancing research discovery","author":"Adams","year":"2018","journal-title":"Digit. Sci."},{"key":"mlstabd614bib773","article-title":"Technology networks: analysis and separations","author":"Gleichmann","year":"2020"},{"key":"mlstabd614bib774","article-title":"Purchasing an electron microscope?\u2014considerations and scientific strategies to help in the decision making process","author":"Owen","year":"2018","journal-title":"Microscopy"},{"key":"mlstabd614bib775","author":"","year":"2020"},{"key":"mlstabd614bib776","author":"","year":"2020"},{"key":"mlstabd614bib777","author":"","year":"2020"},{"key":"mlstabd614bib778","author":"","year":"2020"},{"key":"mlstabd614bib779","author":"","year":"2020"},{"key":"mlstabd614bib780","author":"Ichimiya","year":"2004"},{"key":"mlstabd614bib781","volume":"vol 154","author":"Braun","year":"1999"},{"key":"mlstabd614bib782","doi-asserted-by":"publisher","DOI":"10.1088\/0957-4484\/27\/48\/485703","article-title":"Reflection high-energy electron diffraction measurements of reciprocal space structure of 2D materials","volume":"27","author":"Xiang","year":"2016","journal-title":"Nanotechnology"},{"key":"mlstabd614bib783","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/S0042-207X(02)00714-5","article-title":"Reflection high-energy electron loss spectroscopy (RHEELS): a new approach in the investigation of epitaxial thin film growth by reflection high-energy electron diffraction (RHEED)","volume":"71","author":"Ma\u0161ek","year":"2003","journal-title":"Vacuum"},{"key":"mlstabd614bib784","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1063\/1.104685","article-title":"Reflection electron energy loss spectroscopy during initial stages of Ge growth on Si by molecular beam epitaxy","volume":"58","author":"Atwater","year":"1991","journal-title":"Appl. Phys. Lett."},{"key":"mlstabd614bib785","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultramic.2020.113017","article-title":"Aberration corrected spin polarized low energy electron microscope","volume":"216","author":"Yu","year":"2020","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib786","first-page":"p 2","author":"Bauer","year":"2019"},{"key":"mlstabd614bib787","first-page":"L50","article-title":"A study of chiral magnetic stripe domains within an in-plane virtual magnetic field using SPLEEM","volume":"2017","author":"Li","year":"2017","journal-title":"APS"},{"key":"mlstabd614bib788","first-page":"39","article-title":"Auger electron spectroscopy","author":"Matsui","year":"2018"},{"key":"mlstabd614bib789","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1063\/1.1653933","article-title":"Auger electron spectroscopy in the scanning electron microscope: auger electron images","volume":"19","author":"MacDonald","year":"1971","journal-title":"Appl. Phys. Lett."},{"key":"mlstabd614bib790","article-title":"Energy dispersive x-ray (EDX) microanalysis: a powerful tool in biomedical research and diagnosis","volume":"62","author":"Scimeca","year":"2018","journal-title":"Eur. J. Histochem."},{"key":"mlstabd614bib791","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/j.ultramic.2016.05.008","article-title":"Quantitative atomic resolution elemental mapping via absolute-scale energy dispersive x-ray spectroscopy","volume":"168","author":"Chen","year":"2016","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib792","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899X\/304\/1\/012005","article-title":"Benefits from bremsstrahlung distribution evaluation to get unknown information from specimen in SEM and TEM","volume":"304","author":"Eggert","year":"2018","journal-title":"IOP Conf. Ser.: Mater. Sci. Eng."},{"key":"mlstabd614bib793","doi-asserted-by":"publisher","DOI":"10.1063\/1.4954402","article-title":"CODATA recommended values of the fundamental physical constants: 2014","volume":"45","author":"Mohr","year":"2016","journal-title":"J. Phys. Chem. Ref. Data"},{"key":"mlstabd614bib794","first-page":"569","author":"Romano","year":"2018"},{"key":"mlstabd614bib795","author":"French","year":"2017"},{"key":"mlstabd614bib796","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1080\/14786447908639684","article-title":"XXXI. Investigations in optics, with special reference to the spectroscope","volume":"8","author":"Rayleigh","year":"1879","journal-title":"London, Edinburgh Dublin Phil. Mag. J. Sci."},{"key":"mlstabd614bib797","doi-asserted-by":"publisher","first-page":"4457","DOI":"10.1073\/pnas.0508047103","article-title":"Beyond rayleigh\u2019s criterion: a resolution measure with application to single-molecule microscopy","volume":"103","author":"Ram","year":"2006","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstabd614bib798","author":"","year":"2020"},{"key":"mlstabd614bib799","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1119\/1.4941569","article-title":"The principle of relativity and the de broglie relation","volume":"84","author":"G\u00fc\u00e9mez","year":"2016","journal-title":"Am. J. Phys."},{"key":"mlstabd614bib800","doi-asserted-by":"publisher","first-page":"1047","DOI":"10.1119\/1.10583","article-title":"De Broglie\u2019s thesis: a critical retrospective","volume":"44","author":"MacKinnon","year":"1976","journal-title":"Am. J. Phys."},{"key":"mlstabd614bib801","author":"","year":"2020"},{"key":"mlstabd614bib802","author":"","year":"2020"},{"key":"mlstabd614bib803","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6455\/aa6c4a","article-title":"High-precision measurement of the x-ray Cu K\u03b1 spectrum","volume":"50","author":"Mendenhall","year":"2017","journal-title":"J. Phys. B: At. Mol. Opt. Phys."},{"key":"mlstabd614bib804","author":"","year":"2020"},{"key":"mlstabd614bib805","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1016\/j.ultramic.2016.11.008","article-title":"Spatial coherence of electron beams from field emitters and its effect on the resolution of imaged objects","volume":"175","author":"Latychevskaia","year":"2017","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib806","doi-asserted-by":"publisher","first-page":"894","DOI":"10.1016\/j.ultramic.2011.01.007","article-title":"Persistent misconceptions about incoherence in electron microscopy","volume":"111","author":"Van Dyck","year":"2011","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib807","article-title":"Properties of electrons, their interactions with matter and applications in electron microscopy","author":"Krumeich","year":"2011","journal-title":"Lab. Inorg. Chem."},{"key":"mlstabd614bib808","doi-asserted-by":"publisher","first-page":"2735","DOI":"10.1364\/JOSAA.15.002735","article-title":"Field theory for generalized bidirectional reflectivity: derivation of Helmholtz\u2019s reciprocity principle and Kirchhoff\u2019s law","volume":"15","author":"Greffet","year":"1998","journal-title":"J. Opt. Soc. Am. A"},{"key":"mlstabd614bib809","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1177\/14771535850170010301","article-title":"Helmholtz reciprocity: its validity and application to reflectometry","volume":"17","author":"Clarke","year":"1985","journal-title":"Light. Res. Technol."},{"key":"mlstabd614bib810","doi-asserted-by":"publisher","first-page":"2114","DOI":"10.1017\/S1431927605507761","article-title":"On the reciprocity of TEM and STEM","volume":"11","author":"Rose","year":"2005","journal-title":"Microsc. Microanal."},{"key":"mlstabd614bib811","article-title":"Structure and ferroelectricity at the atomic level in perovskite oxides","author":"Peters","year":"2017"},{"key":"mlstabd614bib812","doi-asserted-by":"publisher","first-page":"1698","DOI":"10.1017\/S1431927610059659","article-title":"Advantages of HAADF vs. conventional TEM imaging for study of PSS-PMB diblock copolymer systems","volume":"16","author":"Yakovlev","year":"2010","journal-title":"Microsc. Microanal."},{"key":"mlstabd614bib813","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1017\/S1431927617000964","article-title":"STEM and TEM: disparate magnification definitions and a way out","volume":"23","author":"Voelkl","year":"2017","journal-title":"Microsc. Microanal."},{"key":"mlstabd614bib814","doi-asserted-by":"publisher","first-page":"997","DOI":"10.6028\/jres.106.051","article-title":"Electron diffraction using transmission electron microscopy","volume":"106","author":"Bendersky","year":"2001","journal-title":"J. Res. Natl Inst. Stand. Technol."},{"key":"mlstabd614bib815","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ultramic.2018.12.007","article-title":"Structure refinement from \u2018digital\u2019 large angle convergent beam electron diffraction patterns","volume":"198","author":"Hubert","year":"2019","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib816","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1107\/S0108767313010143","article-title":"Digital electron diffraction\u2014seeing the whole picture","volume":"69","author":"Beanland","year":"2013","journal-title":"Acta Crystallogr. A"},{"key":"mlstabd614bib817","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1107\/S0108767393010426","article-title":"Convergent-beam electron diffraction","volume":"50","author":"Tanaka","year":"1994","journal-title":"Acta Crystallogr. A"},{"key":"mlstabd614bib818","doi-asserted-by":"crossref","DOI":"10.1557\/mrs.2020.87","article-title":"Electron tomography for functional nanomaterials","author":"Hovden","year":"2020"},{"key":"mlstabd614bib819","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1016\/j.matchar.2019.02.009","article-title":"Fast electron tomography: applications to beam sensitive samples and in situ TEM or operando environmental TEM studies","volume":"151","author":"Koneti","year":"2019","journal-title":"Mater. Charact."},{"key":"mlstabd614bib820","doi-asserted-by":"publisher","DOI":"10.1002\/adma.201801564","article-title":"Electron tomography: a unique tool solving intricate hollow nanostructures","volume":"31","author":"Song","year":"2019","journal-title":"Adv. Mater."},{"key":"mlstabd614bib821","doi-asserted-by":"crossref","first-page":"1161","DOI":"10.1038\/s41592-019-0591-8","article-title":"A complete data processing workflow for Cryo-ET and subtomogram averaging","volume":"16","author":"Chen","year":"2019","journal-title":"Nat. Methods"},{"key":"mlstabd614bib822","doi-asserted-by":"publisher","first-page":"5638","DOI":"10.1002\/adma.201501015","article-title":"Electron tomography: a three-dimensional analytic tool for hard and soft materials research","volume":"27","author":"Ercius","year":"2015","journal-title":"Adv. Mater."},{"key":"mlstabd614bib823","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/S1369-7021(04)00569-3","article-title":"Electron tomography","volume":"7","author":"Weyland","year":"2004","journal-title":"Mater. Today"},{"key":"mlstabd614bib824","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1089\/cmb.2019.0287","article-title":"A consensus framework of distributed multiple-tilt reconstruction in electron tomography","volume":"27","author":"Wang","year":"2020","journal-title":"J. Comput. Biol."},{"key":"mlstabd614bib825","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1038\/nmeth.4115","article-title":"Cryo-electron tomography","volume":"14","author":"Doerr","year":"2017","journal-title":"Nat. Methods"},{"key":"mlstabd614bib826","volume":"vol 1","author":"\u00d6ktem","year":"2015"},{"key":"mlstabd614bib827","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultramic.2020.113023","article-title":"TEM bright field imaging of thick specimens: nodes in thon ring patterns","volume":"216","author":"Tichelaar","year":"2020","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib828","doi-asserted-by":"publisher","first-page":"1612","DOI":"10.1017\/S1431927618008541","article-title":"Toward quantitative bright field TEM imaging of ultra thin samples","volume":"24","author":"Fujii","year":"2018","journal-title":"Microsc. Microanal."},{"key":"mlstabd614bib829","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1016\/S0010-2180(97)00171-5","article-title":"Soot precursor carbonization: visualization using LIF and LII and comparison using bright and dark field TEM","volume":"112","author":"Vander Wal","year":"1998","journal-title":"Combust. Flame"},{"key":"mlstabd614bib830","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1016\/j.ssc.2004.03.035","article-title":"Annular dark field imaging in a TEM","volume":"130","author":"Bals","year":"2004","journal-title":"Solid State Commun."},{"key":"mlstabd614bib831","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-018-20377-2","article-title":"Phase contrast scanning transmission electron microscopy imaging of light and heavy atoms at the limit of contrast and resolution","volume":"8","author":"Y\u00fccelen","year":"2018","journal-title":"Sci. Rep."},{"key":"mlstabd614bib832","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.ultramic.2016.03.006","article-title":"Pixelated detectors and improved efficiency for magnetic imaging in STEM differential phase contrast","volume":"165","author":"Krajnak","year":"2016","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib833","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1016\/j.ultramic.2015.10.011","article-title":"Phase contrast STEM for thin samples: integrated differential phase contrast","volume":"160","author":"Lazi\u0107","year":"2016","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib834","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.ultramic.2018.12.018","article-title":"Comparison of first moment STEM with conventional differential phase contrast and the dependence on electron dose","volume":"203","author":"M\u00fcller-Caspary","year":"2019","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib835","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1016\/j.ultramic.2015.10.008","article-title":"Sample tilt effects on atom column position determination in ABF-STEM imaging","volume":"160","author":"Zhou","year":"2016","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib836","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1017\/s1431927609093891","article-title":"Visualization of light elements at ultrahigh resolution by STEM annular bright field microscopy","volume":"15","author":"Okunishi","year":"2009","journal-title":"Microsc. Microanal."},{"key":"mlstabd614bib837","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.116.246101","article-title":"Unscrambling mixed elements using high angle annular dark field scanning transmission electron microscopy","volume":"116","author":"Van den Bos","year":"2016","journal-title":"Phys. Rev. Lett."},{"key":"mlstabd614bib838","first-page":"1","volume":"vol 579","author":"McMullan","year":"2016"},{"key":"mlstabd614bib839","doi-asserted-by":"publisher","first-page":"1126","DOI":"10.1016\/j.ultramic.2009.04.002","article-title":"Detective quantum efficiency of electron area detectors in electron microscopy","volume":"109","author":"McMullan","year":"2009","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib840","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.ultramic.2017.11.010","article-title":"Clustering analysis strategies for electron energy loss spectroscopy (EELS)","volume":"185","author":"Torruella","year":"2018","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib841","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1557\/mrs.2018.148","article-title":"Ultrafast electron energy-loss spectroscopy in transmission electron microscopy","volume":"43","author":"Pomarico","year":"2018","journal-title":"MRS Bull."},{"key":"mlstabd614bib842","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6501\/28\/1\/015904","article-title":"Analytical electron microscope based on scanning transmission electron microscope with wavelength dispersive x-ray spectroscopy to realize highly sensitive elemental imaging especially for light elements","volume":"28","author":"Koguchi","year":"2016","journal-title":"Meas. Sci. Technol."},{"key":"mlstabd614bib843","doi-asserted-by":"publisher","first-page":"1427","DOI":"10.1016\/j.ultramic.2008.05.011","article-title":"X-ray analysis and mapping by wavelength dispersive x-ray spectroscopy in an electron microscope","volume":"108","author":"Tanaka","year":"2008","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib844","volume":"vol 2","author":"Schwartz","year":"2009"},{"key":"mlstabd614bib845","doi-asserted-by":"publisher","first-page":"3833","DOI":"10.1023\/A:1017973432592","article-title":"Review grain and subgrain characterisation by electron backscatter diffraction","volume":"36","author":"Humphreys","year":"2001","journal-title":"J. Mater. Sci."},{"key":"mlstabd614bib846","first-page":"15","article-title":"Physics-based simulation models for EBSD: advances and challenges","volume":"12","author":"Winkelmann","year":"2016","journal-title":"Nanoscale"},{"key":"mlstabd614bib847","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1017\/S1431927611000055","article-title":"A review of strain analysis using electron backscatter diffraction","volume":"17","author":"Wright","year":"2011","journal-title":"Microsc. Microanal."},{"key":"mlstabd614bib848","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1016\/j.spmi.2008.10.046","article-title":"Mapping strains at the nanoscale using electron back scatter diffraction","volume":"45","author":"Wilkinson","year":"2009","journal-title":"Superlattices Microstruct."},{"key":"mlstabd614bib849","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/j.ultramic.2005.10.001","article-title":"High-resolution elastic strain measurement from electron backscatter diffraction patterns: new levels of sensitivity","volume":"106","author":"Wilkinson","year":"2006","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib850","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-67816-7","article-title":"Y2O3\u2013Al2O3 microsphere crystallization analyzed by electron backscatter diffraction (EBSD)","volume":"10","author":"Wisniewski","year":"2020","journal-title":"Sci. Rep."},{"key":"mlstabd614bib851","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.matchar.2016.04.024","article-title":"Determination of grain boundary mobility during recrystallization by statistical evaluation of electron backscatter diffraction measurements","volume":"117","author":"Basu","year":"2016","journal-title":"Mater. Charact."},{"key":"mlstabd614bib852","doi-asserted-by":"publisher","first-page":"899","DOI":"10.1016\/j.scriptamat.2009.07.020","article-title":"Dynamic recrystallization in the particle\/particle interfacial region of cold-sprayed nickel coating: electron backscatter diffraction characterization","volume":"61","author":"Zou","year":"2009","journal-title":"Scr. Mater."},{"key":"mlstabd614bib853","article-title":"Image simulation in transmission electron microscopy","author":"Kirkland","year":"2006"},{"key":"mlstabd614bib854","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1107\/S205327331501757X","article-title":"Computation in electron microscopy","volume":"72","author":"Kirkland","year":"2016","journal-title":"Acta Crystallogr. A"},{"key":"mlstabd614bib855","author":"Kirkland","year":"2010"},{"key":"mlstabd614bib856","author":"","year":"2017"},{"key":"mlstabd614bib857","article-title":"Advances in computational methods for transmission electron microscopy simulation and image processing","author":"Dyson","year":"2014"},{"key":"mlstabd614bib858","author":"Peters","year":"2019"},{"key":"mlstabd614bib859","author":"","year":"2018"},{"key":"mlstabd614bib860","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ultramic.2018.06.003","article-title":"Dr. Probe: a software for high-resolution stem image simulation","volume":"193","author":"Barthel","year":"2018","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib861","article-title":"Dr. Probe\u2014STEM image simulation software","author":"Barthel","year":"2020"},{"key":"mlstabd614bib862","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1017\/S143192761700174X","article-title":"EMsoft: open source software for electron diffraction\/image simulations","volume":"23","author":"Singh","year":"2017","journal-title":"Microsc. Microanal."},{"key":"mlstabd614bib863","author":"","year":"2020"},{"key":"mlstabd614bib864","author":"Stadelmann","year":"2015"},{"key":"mlstabd614bib865","author":"Zuo","year":"2013"},{"key":"mlstabd614bib866","first-page":"531","article-title":"Accurate and fast electron microscopy simulations using the open source MULTEM program","author":"Lobato","year":"2016"},{"key":"mlstabd614bib867","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.ultramic.2016.06.003","article-title":"Progress and new advances in simulating electron microscopy datasets using MULTEM","volume":"168","author":"Lobato","year":"2016","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib868","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.ultramic.2015.04.016","article-title":"MULTEM: a new multislice program to perform accurate and fast electron diffraction and imaging simulations using graphics processing units with CUDA","volume":"156","author":"Lobato","year":"2015","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib869","article-title":"Advances in high-resolution image simulation","author":"O\u2019Keefe","year":"1988"},{"key":"mlstabd614bib870","author":"","year":"2020"},{"key":"mlstabd614bib871","author":"","year":"2020"},{"key":"mlstabd614bib872","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1186\/s40679-017-0048-z","article-title":"A streaming multi-GPU implementation of image simulation algorithms for scanning transmission electron eicroscopy","volume":"3","author":"Pryor","year":"2017","journal-title":"Adv. Struc. Chem. Imaging"},{"key":"mlstabd614bib873","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1186\/s40679-017-0046-1","article-title":"A fast image simulation algorithm for scanning transmission electron microscopy","volume":"3","author":"Ophus","year":"2017","journal-title":"Adv. Struct. Chem. Imaging"},{"key":"mlstabd614bib874","author":"","year":"2020"},{"key":"mlstabd614bib875","author":"","year":"2020"},{"key":"mlstabd614bib876","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.ultramic.2009.09.010","article-title":"Simulatem: multislice simulations for general objects","volume":"110","author":"G\u00f3mez-Rodr\u00edguez","year":"2010","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib877","author":"","year":"2020"},{"key":"mlstabd614bib878","author":"","year":"2020"},{"key":"mlstabd614bib879","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/S0304-3991(01)00145-0","article-title":"A practical approach for stem image simulation based on the FFT multislice method","volume":"90","author":"Ishizuka","year":"2002","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib880","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1093\/jmicro\/50.4.291","article-title":"Prospects of atomic resolution imaging with an aberration-corrected STEM","volume":"50","author":"Ishizuka","year":"2001","journal-title":"Microscopy"},{"key":"mlstabd614bib881","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1107\/S0567739482001594","article-title":"Multislice formula for inclined illumination","volume":"38","author":"Ishizuka","year":"1982","journal-title":"Acta Crystallogr. A"},{"key":"mlstabd614bib882","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/0304-3991(80)90011-X","article-title":"Contrast transfer of crystal images in TEM","volume":"5","author":"Ishizuka","year":"1980","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib883","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1107\/S0567739477001879","article-title":"A new theoretical and practical approach to the multislice method","volume":"33","author":"Ishizuka","year":"1977","journal-title":"Acta Crystallogr. A"},{"key":"mlstabd614bib884","author":"","year":"2020"},{"key":"mlstabd614bib885","doi-asserted-by":"crossref","DOI":"10.1101\/2020.06.14.20130823","article-title":"Publish or perish: reporting characteristics of peer-reviewed publications, pre-prints and registered studies on the COVID-19 pandemic","author":"Gianola","year":"2020"},{"key":"mlstabd614bib886","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1111\/isj.12289","article-title":"Predatory journals: a sign of an unhealthy publish or perish game?","volume":"30","author":"Nielsen","year":"2020","journal-title":"Inf. Syst. J."},{"key":"mlstabd614bib887","doi-asserted-by":"publisher","first-page":"617","DOI":"10.1007\/s11948-017-0015-z","article-title":"The problem is not professional publishing, but the publish-or-perish culture","volume":"25","author":"G\u00e9nova","year":"2019","journal-title":"Sci. Eng. Ethics"},{"key":"mlstabd614bib888","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1016\/0304-3991(94)00190-X","article-title":"On the beam selection and convergence in the bloch-wave method","volume":"57","author":"Zuo","year":"1995","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib889","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.micron.2017.04.007","article-title":"Quantitative comparison between real space and bloch wave methods in image simulation","volume":"100","author":"Yang","year":"2017","journal-title":"Micron"},{"key":"mlstabd614bib890","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1093\/jmicro\/53.3.257","article-title":"HAADF-STEM imaging with sub-angstrom probes: a full bloch wave analysis","volume":"53","author":"Peng","year":"2004","journal-title":"J. Electron Microsc."},{"key":"mlstabd614bib891","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/aae8f1","article-title":"Bohmian trajectory-bloch wave approach to dynamical simulation of electron diffraction in crystal","volume":"20","author":"Cheng","year":"2018","journal-title":"New J. Phys."},{"key":"mlstabd614bib892","article-title":"Felix","author":"Beanland","year":"2020"},{"key":"mlstabd614bib893","doi-asserted-by":"publisher","first-page":"1203","DOI":"10.1016\/j.ultramic.2009.05.007","article-title":"Bloch-wave-based STEM image simulation with layer-by-layer representation","volume":"109","author":"Morimura","year":"2009","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib894","author":"","year":"2020"},{"key":"mlstabd614bib895","author":"","year":"2020"},{"key":"mlstabd614bib896","author":"","year":"2020"},{"key":"mlstabd614bib897","article-title":"TemDM: software for tem in digitalmicrograph","author":"Potapov","year":"2020"},{"key":"mlstabd614bib898","article-title":"Electron microscopy software","author":"Koch","year":"2016"},{"key":"mlstabd614bib899","article-title":"\u2018How to script\u2026\u2019\u2014digital micrograph scripting handbook","author":"Schaffer","year":"2015"},{"key":"mlstabd614bib900","article-title":"A guide to compiling C++ code to create plugins for DigitalMicrograph (GMS 2.x)","author":"Mitchell","year":"2014"},{"key":"mlstabd614bib901","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1017\/S1431927619001909","article-title":"Real-time data processing using python in digitalmicrograph","volume":"25","author":"Miller","year":"2019","journal-title":"Microsc. Microanal."},{"key":"mlstabd614bib902","article-title":"RAM disks explained: what they are and why you probably shouldn\u2019t use one","author":"Hoffman","year":"2019"},{"key":"mlstabd614bib903","article-title":"Digital storage and memory technology (part 1)","author":"Coughlin","year":"2017"},{"key":"mlstabd614bib904","author":"","year":"2020"},{"key":"mlstabd614bib905","article-title":"TCP socket plug-in for gatan microscopy suite 3.x","author":"Rene de Cotret","year":"2019"},{"key":"mlstabd614bib906","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1038\/s41592-019-0396-9","article-title":"Software tools for automated transmission electron microscopy","volume":"16","author":"Schorb","year":"2019","journal-title":"Nat. Methods"},{"key":"mlstabd614bib907","article-title":"DM stack builder","author":"Peters","year":"2018"},{"key":"mlstabd614bib908","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.ultramic.2013.07.016","article-title":"Weighted simultaneous iterative reconstruction technique for single-axis tomography","volume":"136","author":"Wolf","year":"2014","journal-title":"Ultramicroscopy"},{"key":"mlstabd614bib909","article-title":"Tomography menu","author":"Wolf","year":"2013"},{"key":"mlstabd614bib910","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1002\/mrd.22489","article-title":"The ImageJ ecosystem: an open platform for biomedical image analysis","volume":"82","author":"Schindelin","year":"2015","journal-title":"Mol. Reprod. Dev."},{"key":"mlstabd614bib911","author":"","year":"2020"},{"key":"mlstabd614bib912","author":"","year":"2020"},{"key":"mlstabd614bib913","author":"","year":"2020"},{"key":"mlstabd614bib914","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3320060","article-title":"Demystifying parallel and distributed deep learning: an in-depth concurrency analysis","volume":"52","author":"Ben-Nun","year":"2019","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"mlstabd614bib915","first-page":"1","article-title":"Channel and filter parallelism for large-scale CNN training","author":"Dryden","year":"2019"},{"key":"mlstabd614bib916","article-title":"Activation functions: comparison of trends in practice and research for deep learning","author":"Nwankpa","year":"2018"},{"key":"mlstabd614bib917","article-title":"On the impact of the activation function on deep neural networks training","author":"Hayou","year":"2019"},{"key":"mlstabd614bib918","article-title":"Deep learning neurons versus biological neurons","author":"Roos","year":"2019"},{"key":"mlstabd614bib919","first-page":"907","article-title":"The power of depth for feedforward neural networks","author":"Eldan","year":"2016"},{"key":"mlstabd614bib920","article-title":"Benefits of depth in neural networks","author":"Telgarsky","year":"2016"},{"key":"mlstabd614bib921","first-page":"2654","article-title":"Do deep nets really need to be deep?","author":"Ba","year":"2014"},{"key":"mlstabd614bib922","first-page":"8572","article-title":"Wide neural networks of any depth evolve as linear models under gradient descent","author":"Lee","year":"2019"},{"key":"mlstabd614bib923","article-title":"Small nonlinearities in activation functions create bad local minima in neural networks","author":"Yun","year":"2018"},{"key":"mlstabd614bib924","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"Nair","year":"2010"},{"key":"mlstabd614bib925","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"Glorot","year":"2011"},{"key":"mlstabd614bib926","first-page":"p 3","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume":"vol 30","author":"Maas","year":"2013"},{"key":"mlstabd614bib927","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58529-7_21","article-title":"Dynamic ReLU","author":"Chen","year":"2020"},{"key":"mlstabd614bib928","article-title":"Empirical evaluation of rectified activations in convolutional network","author":"Xu","year":"2015"},{"key":"mlstabd614bib929","article-title":"Comparison of non-linear activation functions for deep neural networks on MNIST classification task","author":"Pedamonti","year":"2018"},{"key":"mlstabd614bib930","article-title":"Leaky ReLU: Improving Traditional ReLU","author":"","year":"2019"},{"key":"mlstabd614bib931","article-title":"The effect of target normalization and momentum on dying ReLU","author":"Arnekvist","year":"2020"},{"key":"mlstabd614bib932","article-title":"Dying ReLU and initialization: theory and numerical examples","author":"Lu","year":"2019"},{"key":"mlstabd614bib933","first-page":"864","article-title":"Why RELU units sometimes die: analysis of single-unit error backpropagation in neural networks","author":"Douglas","year":"2018"},{"key":"mlstabd614bib934","first-page":"1","article-title":"Convolutional deep belief networks on CIFAR-10","volume":"40","author":"Krizhevsky","year":"2010","journal-title":"Tech. Rep."},{"key":"mlstabd614bib935","first-page":"2217","article-title":"Understanding and improving convolutional neural networks via concatenated rectified linear units","author":"Shang","year":"2016"},{"key":"mlstabd614bib936","first-page":"3914","article-title":"Adaptive convolutional ReLUs","author":"Gao","year":"2020"},{"key":"mlstabd614bib937","article-title":"Shifting mean activation towards zero with bipolar activation functions","author":"Eidnes","year":"2017"},{"key":"mlstabd614bib938","doi-asserted-by":"publisher","first-page":"1132","DOI":"10.1016\/j.neucom.2017.09.056","article-title":"Deep neural networks with elastic rectified linear units for object recognition","volume":"275","author":"Jiang","year":"2018","journal-title":"Neurocomputing"},{"key":"mlstabd614bib939","first-page":"1218","article-title":"L* ReLU: piece-wise linear activation functions for deep fine-grained visual categorization","author":"Basirat","year":"2020"},{"key":"mlstabd614bib940","article-title":"Fast and accurate deep network learning by exponential linear units (ELUs)","author":"Clevert","year":"2015"},{"key":"mlstabd614bib941","first-page":"971","article-title":"Self-normalizing neural networks","author":"Klambauer","year":"2017"},{"key":"mlstabd614bib942","article-title":"DeepLABNet: end-to-end learning of deep radial basis networks with fully learnable basis functions","author":"Hryniowski","year":"2019"},{"key":"mlstabd614bib943","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1515\/comp-2016-0005","article-title":"Radial basis function neural networks: a topical state-of-the-art survey","volume":"1","author":"Dash","year":"2016","journal-title":"Open Computer Science"},{"key":"mlstabd614bib944","article-title":"Introduction to radial basis function networks","author":"Orr","year":"1996"},{"key":"mlstabd614bib945","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/72.182710","article-title":"Functional equivalence between radial basis function networks and fuzzy inference systems","volume":"4","author":"Jang","year":"1993","journal-title":"IEEE Trans. Neural Netw."},{"key":"mlstabd614bib946","first-page":"103","article-title":"Computationally efficient radial basis function","author":"Wuraola","year":"2018"},{"key":"mlstabd614bib947","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/j.neucom.2019.10.118","article-title":"A comprehensive survey on support vector machine classification: applications, challenges and trends","volume":"408","author":"Cervantes","year":"2020","journal-title":"Neurocomputing"},{"key":"mlstabd614bib948","author":"Scholkopf","year":"2018"},{"key":"mlstabd614bib949","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3280989","article-title":"Parallel computing of support vector machines: a survey","volume":"51","author":"Tavara","year":"2019","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"mlstabd614bib950","article-title":"K-TanH: hardware efficient activations for deep learning","author":"Kundu","year":"2019"},{"key":"mlstabd614bib951","first-page":"9","author":"LeCun","year":"2012"},{"key":"mlstabd614bib952","first-page":"199","article-title":"Why TanH is a hardware friendly activation function for CNNs","author":"Abdelouahab","year":"2017"},{"key":"mlstabd614bib953","first-page":"3059","article-title":"Noisy activation functions","author":"Gulcehre","year":"2016"},{"key":"mlstabd614bib954","first-page":"p 185","article-title":"On the pairing of the softmax activation and cross-entropy penalty functions and the derivation of the softmax activation function","volume":"vol 181","author":"Dunne","year":"1997"},{"key":"mlstabd614bib955","article-title":"A guide to convolution arithmetic for deep learning","author":"Dumoulin","year":"2018"},{"key":"mlstabd614bib956","article-title":"Fractional max-pooling","author":"Graham","year":"2014"},{"key":"mlstabd614bib957","article-title":"Striving for simplicity: the all convolutional net","author":"Springenberg","year":"2014"},{"key":"mlstabd614bib958","first-page":"3856","article-title":"Dynamic routing between capsules","author":"Sabour","year":"2017"},{"key":"mlstabd614bib959","first-page":"382","article-title":"Cosine normalization: using cosine similarity instead of dot product in neural networks","author":"Luo","year":"2018"},{"key":"mlstabd614bib960","first-page":"145","article-title":"Searching for activation functions using a self-adaptive evolutionary algorithm","author":"Nader","year":"2020"},{"key":"mlstabd614bib961","article-title":"Searching for activation functions","author":"Ramachandran","year":"2018"},{"key":"mlstabd614bib962","article-title":"Discovering parametric activation functions","author":"Bingham","year":"2020"},{"key":"mlstabd614bib963","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.neunet.2018.01.007","article-title":"A novel type of activation function in artificial neural networks: trained activation function","volume":"99","author":"Ertu\u011frul","year":"2018","journal-title":"Neural Netw."},{"key":"mlstabd614bib964","first-page":"686","article-title":"Review of adaptive activation function in deep neural network","author":"Lau","year":"2018"},{"key":"mlstabd614bib965","first-page":"348","article-title":"Deep neural network using trainable activation functions","author":"Chung","year":"2016"},{"key":"mlstabd614bib966","article-title":"Learning activation functions to improve deep neural networks","author":"Agostinelli","year":"2014"},{"key":"mlstabd614bib967","first-page":"1152","article-title":"Beyond weights adaptation: a new neuron model with trainable activation function and its supervised learning","volume":"vol 2","author":"Wu","year":"1997"},{"key":"mlstabd614bib968","article-title":"ProbAct: a probabilistic activation function for deep neural networks","author":"Lee","year":"2019"},{"key":"mlstabd614bib969","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2014"},{"key":"mlstabd614bib970","article-title":"Improving deep neural networks with probabilistic maxout units","author":"Springenberg","year":"2013"},{"key":"mlstabd614bib971","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.eswa.2018.11.042","article-title":"Linearized sigmoidal activation: a novel activation function with tractable non-linear characteristics to boost representation capability","volume":"120","author":"Bawa","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"mlstabd614bib972","article-title":"An overview of normalization methods in deep learning machine learning explained","author":"Kurita","year":"2018"},{"key":"mlstabd614bib973","article-title":"Normalizing the normalizers: comparing and extending network normalization schemes","author":"Ren","year":"2016"},{"key":"mlstabd614bib974","article-title":"Streaming normalization: towards simpler and more biologically-plausible normalizations for online and recurrent learning","author":"Liao","year":"2016"},{"key":"mlstabd614bib975","first-page":"2483","article-title":"How does batch normalization help optimization?","author":"Santurkar","year":"2018"},{"key":"mlstabd614bib976","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015"},{"key":"mlstabd614bib977","first-page":"7694","article-title":"Understanding batch normalization","author":"Bjorck","year":"2018"},{"key":"mlstabd614bib978","article-title":"A mean field theory of batch normalization","author":"Yang","year":"2019"},{"key":"mlstabd614bib979","article-title":"Batch normalization layers","author":"Ioffe","year":"2019"},{"key":"mlstabd614bib980","first-page":"3254","article-title":"Revisit batch normalization: new understanding and refinement via composition optimization","author":"Lian","year":"2019"},{"key":"mlstabd614bib981","first-page":"1","article-title":"Low latency RNN inference with cellular batching","author":"Gao","year":"2018"},{"key":"mlstabd614bib982","first-page":"36","article-title":"Serving deep neural networks at the cloud edge for vision applications on mobile platforms","author":"Fang","year":"2019"},{"key":"mlstabd614bib983","article-title":"Distributed deep learning using synchronous stochastic gradient descent","author":"Das","year":"2016"},{"key":"mlstabd614bib984","article-title":"On large-batch training for deep learning: generalization gap and sharp minima","author":"Keskar","year":"2016"},{"key":"mlstabd614bib985","article-title":"Revisiting small batch training for deep neural networks","author":"Masters","year":"2018"},{"key":"mlstabd614bib986","article-title":"Scaling SGD batch size to 32k for ImageNet training","author":"You","year":"2017"},{"key":"mlstabd614bib987","article-title":"AdaBatch: adaptive batch sizes for training deep neural networks","author":"Devarakonda","year":"2017"},{"key":"mlstabd614bib988","article-title":"Augment your batch: better training with larger batches","author":"Hoffer","year":"2019"},{"key":"mlstabd614bib989","first-page":"1","article-title":"An empirical study on position of the batch normalization layer in convolutional neural networks","author":"Hasani","year":"2019"},{"key":"mlstabd614bib990","article-title":"Batch normalization benchmarks","author":"Mishkin","year":"2016"},{"key":"mlstabd614bib991","article-title":"Evaluating prediction-time batch normalization for robustness under covariate shift","author":"Nado","year":"2020"},{"key":"mlstabd614bib992","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2019\/589","article-title":"Experience replay optimization","author":"Zha","year":"2019"},{"key":"mlstabd614bib993","article-title":"Prioritized experience replay","author":"Schaul","year":"2015"},{"key":"mlstabd614bib994","first-page":"1945","article-title":"Batch renormalization: towards reducing minibatch dependence in batch-normalized models","author":"Ioffe","year":"2017"},{"key":"mlstabd614bib995","first-page":"2234","article-title":"Improved techniques for training GANs","author":"Salimans","year":"2016"},{"key":"mlstabd614bib996","first-page":"8433","article-title":"Online normalization for training neural networks","author":"Chiley","year":"2019"},{"key":"mlstabd614bib997","first-page":"2160","article-title":"Norm matters: efficient and accurate normalization schemes in deep networks","author":"Hoffer","year":"2018"},{"key":"mlstabd614bib998","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"mlstabd614bib999","first-page":"4381","article-title":"Understanding and improving layer normalization","author":"Xu","year":"2019"},{"key":"mlstabd614bib1000","article-title":"Instance normalization: the missing ingredient for fast stylization","author":"Ulyanov","year":"2017"},{"key":"mlstabd614bib1001","doi-asserted-by":"publisher","first-page":"3365","DOI":"10.1109\/TVCG.2019.2921336","article-title":"Neural style transfer: a review","volume":"26","author":"Jing","year":"2019","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"mlstabd614bib1002","first-page":"2414","article-title":"Image style transfer using convolutional neural networks","author":"Gatys","year":"2016"},{"key":"mlstabd614bib1003","article-title":"A neural algorithm of artistic style","author":"Gatys","year":"2015"},{"key":"mlstabd614bib1004","first-page":"2223","article-title":"Unpaired image-to-image translation using cycle-consistent adversarial networks","author":"Zhu","year":"2017"},{"key":"mlstabd614bib1005","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2017\/310","article-title":"Demystifying neural style transfer","author":"Li","year":"2017"},{"key":"mlstabd614bib1006","first-page":"3","article-title":"Group normalization","author":"Wu","year":"2018"},{"key":"mlstabd614bib1007","article-title":"Do normalization layers in a deep ConvNet really need to be distinct?","author":"Luo","year":"2018"},{"key":"mlstabd614bib1008","article-title":"Differentiable learning-to-normalize via switchable normalization","author":"Luo","year":"2018"},{"key":"mlstabd614bib1009","first-page":"2558","article-title":"Batch-instance normalization for adaptively style-invariant neural networks","author":"Nam","year":"2018"},{"key":"mlstabd614bib1010","article-title":"We analyzed 16,625 papers to figure out where AI is headed next","author":"Hao","year":"2019","journal-title":"MIT Technol. Rev."},{"key":"mlstabd614bib1011","article-title":"Recurrent batch normalization","author":"Cooijmans","year":"2016"},{"key":"mlstabd614bib1012","article-title":"Bridging the gaps between residual learning, recurrent neural networks and visual cortex","author":"Liao","year":"2016"},{"key":"mlstabd614bib1013","first-page":"2657","article-title":"Batch normalized recurrent neural networks","author":"Laurent","year":"2016"},{"key":"mlstabd614bib1014","first-page":"901","article-title":"Weight normalization: a simple reparameterization to accelerate training of deep neural networks","author":"Salimans","year":"2016"},{"key":"mlstabd614bib1015","article-title":"Weight standardization","author":"Qiao","year":"2019"},{"key":"mlstabd614bib1016","article-title":"Comparison of batch normalization and weight normalization algorithms for the large-scale image classification","author":"Gitman","year":"2017"},{"key":"mlstabd614bib1017","article-title":"Spectral normalization for generative adversarial networks","author":"Miyato","year":"2018"},{"key":"mlstabd614bib1018","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/BF00229304","article-title":"Estimation of the Lipschitz constant of a function","volume":"8","author":"Wood","year":"1996","journal-title":"J. Glob. Optim."},{"key":"mlstabd614bib1019","article-title":"Machine learning\u2014singular value decomposition (SVD) and principal component analysis (PCA)","author":"Hui","year":"2019"},{"key":"mlstabd614bib1020","article-title":"Singular value decomposition and its applications in principal component analysis","author":"Afham","year":"2020"},{"key":"mlstabd614bib1021","first-page":"91","author":"Wall","year":"2003"},{"key":"mlstabd614bib1022","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1109\/TAC.1980.1102314","article-title":"The singular value decomposition: its computation and some applications","volume":"25","author":"Klema","year":"1980","journal-title":"IEEE Trans. Autom. Control"},{"key":"mlstabd614bib1023","article-title":"Spectral norm regularization for improving the generalizability of deep learning","author":"Yoshida","year":"2017"},{"key":"mlstabd614bib1024","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/S0377-0427(00)00413-1","article-title":"Eigenvalue computation in the 20th century","volume":"123","author":"Golub","year":"2000","journal-title":"J. Comput. Appl. Math."},{"key":"mlstabd614bib1025","article-title":"Transformers without tears: improving the normalization of self-attention","author":"Nguyen","year":"2019"},{"key":"mlstabd614bib1026","article-title":"Improving lexical choice in neural machine translation","author":"Nguyen","year":"2017"},{"key":"mlstabd614bib1027","article-title":"Simple introduction to convolutional neural networks","author":"Stewart","year":"2019"},{"key":"mlstabd614bib1028","first-page":"23","article-title":"Introduction to convolutional neural networks","volume":"5","author":"Wu","year":"2017","journal-title":"National Key Lab for Novel Software Technology"},{"key":"mlstabd614bib1029","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1109\/MSP.2017.2739299","article-title":"Convolutional neural networks for inverse problems in imaging: a review","volume":"34","author":"McCann","year":"2017","journal-title":"IEEE Signal Process. Mag."},{"key":"mlstabd614bib1030","article-title":"An introduction to convolutional neural networks","author":"O\u2019Shea","year":"2015"},{"key":"mlstabd614bib1031","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1113\/jphysiol.1968.sp008455","article-title":"Receptive fields and functional architecture of monkey striate cortex","volume":"195","author":"Hubel","year":"1968","journal-title":"J. Physiol."},{"key":"mlstabd614bib1032","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/BF00344251","article-title":"A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position","volume":"36","author":"Fukushima","year":"1980","journal-title":"Biol. Cybern."},{"key":"mlstabd614bib1033","first-page":"267","author":"Fukushima","year":"1982"},{"key":"mlstabd614bib1034","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/0893-6080(88)90014-7","article-title":"Neocognitron: a hierarchical neural network capable of visual pattern recognition","volume":"1","author":"Fukushima","year":"1988","journal-title":"Neural Netw."},{"key":"mlstabd614bib1035","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/S0925-2312(02)00614-8","article-title":"Neocognitron for handwritten digit recognition","volume":"51","author":"Fukushima","year":"2003","journal-title":"Neurocomputing"},{"key":"mlstabd614bib1036","first-page":"31","article-title":"An artificial neural network for spatio-temporal bipolar patterns: application to phoneme classification","author":"Atlas","year":"1988"},{"key":"mlstabd614bib1037","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"mlstabd614bib1038","first-page":"319","author":"LeCun","year":"1999"},{"key":"mlstabd614bib1039","doi-asserted-by":"publisher","first-page":"3207","DOI":"10.1162\/NECO_a_00052","article-title":"Deep, big, simple neural nets for handwritten digit recognition","volume":"22","author":"Cire\u015fan","year":"2010","journal-title":"Neural Comput."},{"key":"mlstabd614bib1040","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.patrec.2018.05.018","article-title":"A review of convolutional-neural-network-based action recognition","volume":"118","author":"Yao","year":"2019","journal-title":"Pattern Recognit. Lett."},{"key":"mlstabd614bib1041","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1002\/cyto.a.23701","article-title":"Deep learning in image cytometry: a review","volume":"95","author":"Gupta","year":"2019","journal-title":"Cytometry A"},{"key":"mlstabd614bib1042","doi-asserted-by":"publisher","first-page":"1683","DOI":"10.1109\/TCSVT.2019.2910119","article-title":"Image and video compression with neural networks: a review","volume":"30","author":"Ma","year":"2019","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"mlstabd614bib1043","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3357375","article-title":"Deep learning-based video coding: a review and a case study","volume":"53","author":"Liu","year":"2020","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"mlstabd614bib1044","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.neunet.2019.04.024","article-title":"Deep neural network concepts for background subtraction: a systematic review and comparative evaluation","volume":"117","author":"Bouwmans","year":"2019","journal-title":"Neural Netw."},{"key":"mlstabd614bib1045","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1007\/s10916-018-1088-1","article-title":"Medical image analysis using convolutional neural networks: a review","volume":"42","author":"Anwar","year":"2018","journal-title":"J. Med. Syst."},{"key":"mlstabd614bib1046","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1148\/radiol.2018180547","article-title":"Convolutional neural networks for radiologic images: a radiologist\u2019s guide","volume":"290","author":"Soffer","year":"2019","journal-title":"Radiology"},{"key":"mlstabd614bib1047","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/s13244-018-0639-9","article-title":"Convolutional neural networks: an overview and application in radiology","volume":"9","author":"Yamashita","year":"2018","journal-title":"Insights Imaging"},{"key":"mlstabd614bib1048","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.artmed.2018.08.008","article-title":"Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review","volume":"95","author":"Bernal","year":"2019","journal-title":"Artif. Intell. Med."},{"key":"mlstabd614bib1049","doi-asserted-by":"publisher","first-page":"20TR01","DOI":"10.1088\/1361-6560\/ab843e","article-title":"Deep learning in medical image registration: a review","volume":"65","author":"Fu","year":"2020","journal-title":"Phys. Med. Biol."},{"key":"mlstabd614bib1050","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2019.100203","article-title":"Application of deep learning for retinal image analysis: a review","volume":"35","author":"Badar","year":"2020","journal-title":"Comput. Sci. Rev."},{"key":"mlstabd614bib1051","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med. Image Anal."},{"key":"mlstabd614bib1052","doi-asserted-by":"publisher","first-page":"1","DOI":"10.26599\/BDMA.2018.9020001","article-title":"Applications of deep learning to MRI images: a survey","volume":"1","author":"Liu","year":"2018","journal-title":"Big Data Min. Analytics"},{"key":"mlstabd614bib1053","doi-asserted-by":"publisher","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","article-title":"Object detection with deep learning: a review","volume":"30","author":"Zhao","year":"2019","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"mlstabd614bib1054","article-title":"Salient object detection in the deep learning era: an in-depth survey","author":"Wang","year":"2019"},{"key":"mlstabd614bib1055","article-title":"Deep learning based text classification: a comprehensive review","author":"Minaee","year":"2020"},{"key":"mlstabd614bib1056","article-title":"TensorFlow Core v2.2.0 Python Documentation for Convolutional Layer","year":"2020"},{"key":"mlstabd614bib1057","author":"McAndrew","year":"2015"},{"key":"mlstabd614bib1058","article-title":"OpenCV documentation","author":"","year":"2019"},{"key":"mlstabd614bib1059","first-page":"291","article-title":"Edge detection of images using sobel operator","volume":"2","author":"Vairalkar","year":"2012","journal-title":"Int. J. Emerg. Technol. Adv. Eng."},{"key":"mlstabd614bib1060","article-title":"Custom extended sobel filters","author":"Bogdan","year":"2019"},{"key":"mlstabd614bib1061","first-page":"125","volume":"vol 2","author":"J\u00e4hne","year":"1999"},{"key":"mlstabd614bib1062","article-title":"Optimal operators in digital image processing","author":"Scharr","year":"2000"},{"key":"mlstabd614bib1063","doi-asserted-by":"publisher","first-page":"29","DOI":"10.2478\/sgem-2014-0004","article-title":"Edge detection on images of pseudoimpedance section supported by context and adaptive transformation model images","volume":"36","author":"Kawalec-Lata\u0142a","year":"2014","journal-title":"Stud. Geotech. Mech."},{"key":"mlstabd614bib1064","article-title":"Machine perception of three-dimensional solids","author":"Roberts","year":"1963"},{"key":"mlstabd614bib1065","first-page":"15","article-title":"Object enhancement and extraction","volume":"10","author":"Prewitt","year":"1970","journal-title":"Picture Processing and Psychopictorics"},{"key":"mlstabd614bib1066","article-title":"Flattened convolutional neural networks for feedforward acceleration","author":"Jin","year":"2014"},{"key":"mlstabd614bib1067","article-title":"XSepConv: extremely separated convolution","author":"Chen","year":"2020"},{"key":"mlstabd614bib1068","doi-asserted-by":"crossref","DOI":"10.5244\/C.28.88","article-title":"Speeding up convolutional neural networks with low rank expansions","author":"Jaderberg","year":"2014"},{"key":"mlstabd614bib1069","first-page":"1194","article-title":"Convolution with even-sized kernels and symmetric padding","author":"Wu","year":"2019"},{"key":"mlstabd614bib1070","article-title":"Efficient N-dimensional convolutions via higher-order factorization","author":"Kossaifi","year":"2019"},{"key":"mlstabd614bib1071","article-title":"Using constant padding, reflection padding and replication padding with keras","author":"","year":"2020"},{"key":"mlstabd614bib1072","article-title":"Partial convolution based padding","author":"Liu","year":"2018"},{"key":"mlstabd614bib1073","article-title":"FractalNet: ultra-deep neural networks without residuals","author":"Larsson"},{"key":"mlstabd614bib1074","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.11231","article-title":"Inception-v4, Inception-ResNet and the impact of residual connections on learning","author":"Szegedy","year":"2017"},{"key":"mlstabd614bib1075","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"Szegedy","year":"2016"},{"key":"mlstabd614bib1076","first-page":"1","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2015"},{"key":"mlstabd614bib1077","first-page":"8697","article-title":"Learning transferable architectures for scalable image recognition","author":"Zoph","year":"2018"},{"key":"mlstabd614bib1078","first-page":"1637","article-title":"Deeply-recursive convolutional network for image super-resolution","author":"Kim","year":"2016"},{"key":"mlstabd614bib1079","first-page":"3147","article-title":"Image super-resolution via deep recursive residual network","author":"Tai","year":"2017"},{"key":"mlstabd614bib1080","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"mlstabd614bib1081","article-title":"Effects of padding on LSTMs and CNNs","author":"Dwarampudi","year":"2019"},{"key":"mlstabd614bib1082","first-page":"85","article-title":"Image inpainting for irregular holes using partial convolutions","author":"Liu","year":"2018"},{"key":"mlstabd614bib1083","article-title":"Multilayer perceptron algebra","author":"Peng","year":"2017"},{"key":"mlstabd614bib1084","first-page":"1171","article-title":"Automatic construction of multi-layer perceptron network from streaming examples","author":"Pratama","year":"2019"},{"key":"mlstabd614bib1085","article-title":"Towards learning convolutions from scratch","author":"Neyshabur","year":"2020"},{"key":"mlstabd614bib1086","doi-asserted-by":"publisher","first-page":"1892","DOI":"10.1364\/OL.44.001892","article-title":"3D deep encoder\u2013decoder network for fluorescence molecular tomography","volume":"44","author":"Guo","year":"2019","journal-title":"Opt. Lett."},{"key":"mlstabd614bib1087","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1137\/090752286","article-title":"Tensor-train decomposition","volume":"33","author":"Oseledets","year":"2011","journal-title":"SIAM J. Sci. Comput."},{"key":"mlstabd614bib1088","first-page":"442","article-title":"Tensorizing neural networks","author":"Novikov","year":"2015"},{"key":"mlstabd614bib1089","article-title":"Take it in your stride: do we need striding in CNNs?","author":"Kong","year":"2017"},{"key":"mlstabd614bib1090","doi-asserted-by":"crossref","first-page":"13581","DOI":"10.1007\/s11042-019-08385-4","article-title":"On the use of variable stride in convolutional neural networks","volume":"79","author":"Zaniolo","year":"2020","journal-title":"Multimedia Tools Appl."},{"key":"mlstabd614bib1091","article-title":"Is the deconvolution layer the same as a convolutional layer?","author":"Shi","year":"2016"},{"key":"mlstabd614bib1092","article-title":"Checkerboard artifact free sub-pixel convolution: a note on sub-pixel convolution, resize convolution and convolution resize","author":"Aitken","year":"2017"},{"key":"mlstabd614bib1093","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00003","article-title":"Deconvolution and checkerboard artifacts","volume":"1","author":"Odena","year":"2016","journal-title":"Distill"},{"key":"mlstabd614bib1094","article-title":"MobileNets: efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"mlstabd614bib1095","article-title":"Network decoupling: from regular to depthwise separable convolutions","author":"Guo","year":"2018"},{"key":"mlstabd614bib1096","author":"","year":"2020"},{"key":"mlstabd614bib1097","article-title":"Depth-wise separable convolutions: performance investigations","author":"Liu","year":"2020"},{"key":"mlstabd614bib1098","first-page":"325","author":"Gunther","year":"2019"},{"key":"mlstabd614bib1099","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1038\/eye.2015.236","article-title":"Why rods and cones?","volume":"30","author":"Lamb","year":"2016","journal-title":"Eye"},{"key":"mlstabd614bib1100","first-page":"63","author":"Cohen","year":"1972"},{"key":"mlstabd614bib1101","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstabd614bib1102","article-title":"Image recognition using scale recurrent neural networks","author":"Zhang","year":"2018"},{"key":"mlstabd614bib1103","first-page":"219","author":"Tanaka","year":"2017"},{"key":"mlstabd614bib1104","author":"","year":"2020"},{"key":"mlstabd614bib1105","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1109\/JPROC.2004.840301","article-title":"The design and implementation of FFTW3","volume":"93","author":"Frigo","year":"2005","journal-title":"Proc. IEEE"},{"key":"mlstabd614bib1106","first-page":"511","article-title":"The fast Fourier transform partitioning scheme for GPU\u2019s computation effectiveness improvement","author":"Stokfiszewski","year":"2017"},{"key":"mlstabd614bib1107","first-page":"315","article-title":"Large-scale FFT on GPU clusters","author":"Chen","year":"2010"},{"key":"mlstabd614bib1108","first-page":"305","article-title":"An empirically tuned 2D and 3D FFT library on CUDA GPU","author":"Gu","year":"2010"},{"key":"mlstabd614bib1109","first-page":"162","article-title":"Effectiveness of fast Fourier transform implementations on GPU and CPU","author":"Pucha\u0142a","year":"2015"},{"key":"mlstabd614bib1110","first-page":"1","article-title":"An efficient, model-based CPU-GPU heterogeneous FFT library","author":"Ogata","year":"2008"},{"key":"mlstabd614bib1111","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1090\/S0025-5718-1965-0178586-1","article-title":"An algorithm for the machine calculation of complex Fourier series","volume":"19","author":"Cooley","year":"1965","journal-title":"Math. Comput."},{"key":"mlstabd614bib1112","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1016\/0165-1684(90)90158-U","article-title":"Fast Fourier transforms: a tutorial review and a state of the art","volume":"19","author":"Duhamel","year":"1990","journal-title":"Signal Process."},{"key":"mlstabd614bib1113","author":"","year":"2017"},{"key":"mlstabd614bib1114","article-title":"Very efficient training of convolutional neural networks using fast Fourier transform and overlap-and-add","author":"Highlander","year":"2016"},{"key":"mlstabd614bib1115","article-title":"Convolution theorem","author":"Weisstein","year":"2020"},{"key":"mlstabd614bib1116","first-page":"786","article-title":"FCNN: Fourier convolutional neural networks","author":"Pratt","year":"2017"},{"key":"mlstabd614bib1117","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"mlstabd614bib1118","first-page":"13","article-title":"Neocortical layer 6, a review","volume":"4","author":"Thomson","year":"2010","journal-title":"Frontiers Neuroanat."},{"key":"mlstabd614bib1119","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1093\/cercor\/6.3.329","article-title":"The functional organization of local circuits in visual cortex: insights from the study of tree shrew striate cortex","volume":"6","author":"Fitzpatrick","year":"1996","journal-title":"Cereb. Cortex"},{"key":"mlstabd614bib1120","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2990339","article-title":"Norm-preservation: why residual networks can become extremely deep?","author":"Zaeemzadeh","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstabd614bib1121","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.neunet.2019.06.009","article-title":"Depth with nonlinearity creates no bad local minima in ResNets","volume":"118","author":"Kawaguchi","year":"2019","journal-title":"Neural Netw."},{"key":"mlstabd614bib1122","first-page":"6389","article-title":"Visualizing the loss landscape of neural nets","author":"Li","year":"2018"},{"key":"mlstabd614bib1123","first-page":"550","article-title":"Residual networks behave like ensembles of relatively shallow networks","author":"Veit","year":"2016"},{"key":"mlstabd614bib1124","article-title":"Highway and residual networks learn unrolled iterative estimation","author":"Greff","year":"2016"},{"key":"mlstabd614bib1125","first-page":"2640","article-title":"A simple yet effective baseline for 3D human pose estimation","author":"Martinez","year":"2017"},{"key":"mlstabd614bib1126","doi-asserted-by":"publisher","first-page":"56","DOI":"10.3390\/info9030056","article-title":"Residual recurrent neural networks for learning sequential representations","volume":"9","author":"Yue","year":"2018","journal-title":"Information"},{"key":"mlstabd614bib1127","first-page":"1591","article-title":"Residual LSTM: design of a deep recurrent architecture for distant speech recognition","author":"Kim","year":"2017"},{"key":"mlstabd614bib1128","article-title":"Google\u2019s neural machine translation system: bridging the gap between human and machine translation","author":"Wu","year":"2016"},{"key":"mlstabd614bib1129","first-page":"2377","article-title":"Training very deep networks","author":"Srivastava","year":"2015"},{"key":"mlstabd614bib1130","article-title":"Highway networks","author":"Srivastava","year":"2015"},{"key":"mlstabd614bib1131","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2918284","article-title":"Convolutional networks with dense connectivity","author":"Huang","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstabd614bib1132","first-page":"4700","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"mlstabd614bib1133","first-page":"4799","article-title":"Image super-resolution using dense skip connections","author":"Tong","year":"2017"},{"key":"mlstabd614bib1134","doi-asserted-by":"publisher","first-page":"3007","DOI":"10.1109\/TCSVT.2017.2734838","article-title":"An end-to-end compression framework based on convolutional neural networks","volume":"28","author":"Jiang","year":"2017","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"mlstabd614bib1135","first-page":"7103","article-title":"Mean field residual networks: on the edge of chaos","author":"Yang","year":"2017"},{"key":"mlstabd614bib1136","first-page":"5393","article-title":"Dynamical isometry and a mean field theory of CNNs: how to train 10,000-layer vanilla convolutional neural networks","author":"Xiao","year":"2018"},{"key":"mlstabd614bib1137","doi-asserted-by":"publisher","first-page":"1572","DOI":"10.3390\/en12081572","article-title":"Concatenate convolutional neural networks for non-intrusive load monitoring across complex background","volume":"12","author":"Wu","year":"2019","journal-title":"Energies"},{"key":"mlstabd614bib1138","first-page":"2275","article-title":"Vertex reconstruction of neutrino interactions using deep learning","author":"Terwilliger","year":"2017"},{"key":"mlstabd614bib1139","first-page":"115","article-title":"Learning precise timing with LSTM recurrent networks","volume":"3","author":"Gers","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"mlstabd614bib1140","doi-asserted-by":"publisher","first-page":"1333","DOI":"10.1109\/72.963769","article-title":"LSTM recurrent networks learn simple context-free and context-sensitive languages","volume":"12","author":"Gers","year":"2001","journal-title":"IEEE Trans. Neural Netw."},{"key":"mlstabd614bib1141","article-title":"Network-in-network","author":"Lin","year":"2013"},{"key":"mlstabd614bib1142","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"mlstabd614bib1143","article-title":"The illustrated transformer","author":"Alammar","year":"2018"},{"key":"mlstabd614bib1144","first-page":"2204","article-title":"Recurrent models of visual attention","author":"Mnih","year":"2014"},{"key":"mlstabd614bib1145","article-title":"Multiple object recognition with visual attention","author":"Ba","year":"2014"},{"key":"mlstabd614bib1146","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015"},{"key":"mlstabd614bib1147","article-title":"Memory-based control with recurrent neural networks","author":"Heess","year":"2015"},{"key":"mlstabd614bib1148","first-page":"1008","article-title":"Actor-critic algorithms","author":"Konda","year":"2000"},{"key":"mlstabd614bib1149","article-title":"Learning surrogate losses","author":"Grabocka","year":"2019"},{"key":"mlstabd614bib1150","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/MSP.2019.2931595","article-title":"Surrogate gradient learning in spiking neural networks","volume":"36","author":"Neftci","year":"2019","journal-title":"IEEE Signal Process. Mag."},{"key":"mlstabd614bib1151","article-title":"Generative adversarial network training is a continual learning problem","author":"Liang","year":"2018"},{"key":"mlstabd614bib1152","first-page":"1627","article-title":"Decoupled neural interfaces using synthetic gradients","author":"Jaderberg","year":"2017"},{"key":"mlstabd614bib1153","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"mlstabd614bib1154","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1109\/TETCI.2020.2991774","article-title":"Loss functions of generative adversarial networks (GANs): opportunities and challenges","volume":"4","author":"Pan","year":"2020","journal-title":"IEEE Trans. on Emerging Topics in Computational Intelligence"},{"key":"mlstabd614bib1155","article-title":"Towards a deeper understanding of adversarial losses","author":"Dong","year":"2019"},{"key":"mlstabd614bib1156","article-title":"Which training methods for gans do actually converge?","author":"Mescheder","year":"2018"},{"key":"mlstabd614bib1157","first-page":"3581","article-title":"A large-scale study on regularization and normalization in GANs","author":"Kurach","year":"2019"},{"key":"mlstabd614bib1158","first-page":"2018","article-title":"Stabilizing training of generative adversarial networks through regularization","author":"Roth","year":"2017"},{"key":"mlstabd614bib1159","first-page":"2672","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014"},{"key":"mlstabd614bib1160","doi-asserted-by":"publisher","first-page":"2947","DOI":"10.1109\/TPAMI.2018.2872043","article-title":"On the effectiveness of least squares generative adversarial networks","volume":"41","author":"Mao","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstabd614bib1161","first-page":"2794","article-title":"Least squares generative adversarial networks","author":"Mao","year":"2017"},{"key":"mlstabd614bib1162","article-title":"Stabilizing generative adversarial network training: a survey","author":"Wiatrak","year":"2019"},{"key":"mlstabd614bib1163","article-title":"MGGAN: solving mode collapse using manifold guided training","author":"Bang","year":"2018"},{"key":"mlstabd614bib1164","first-page":"214","article-title":"Wasserstein generative adversarial networks","author":"Arjovsky","year":"2017"},{"key":"mlstabd614bib1165","first-page":"5767","article-title":"Improved training of wasserstein GANs","author":"Gulrajani","year":"2017"},{"key":"mlstabd614bib1166","first-page":"311","author":"Hazan","year":"2017"},{"key":"mlstabd614bib1167","article-title":"GradNorm: gradient normalization for adaptive loss balancing in deep multitask networks","author":"Chen","year":"2017"},{"key":"mlstabd614bib1168","article-title":"Multitask learning with single gradient step update for task balancing","author":"Lee","year":"2020"},{"key":"mlstabd614bib1169","first-page":"7354","article-title":"Self-attention generative adversarial networks","author":"Zhang","year":"2019"},{"key":"mlstabd614bib1170","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"Brock","year":"2018"},{"key":"mlstabd614bib1171","article-title":"The GAN zoo","author":"Hindupur","year":"2018"},{"key":"mlstabd614bib1172","first-page":"8798","article-title":"High-resolution image synthesis and semantic manipulation with conditional GANs","author":"Wang","year":"2018"},{"key":"mlstabd614bib1173","article-title":"Unsupervised video-to-video translation","author":"Bashkirova","year":"2018"},{"key":"mlstabd614bib1174","first-page":"700","article-title":"Unsupervised image-to-image translation networks","author":"Liu","year":"2017"},{"key":"mlstabd614bib1175","first-page":"8983","article-title":"TraVeLGAN: image-to-image translation by transformation vector learning","author":"Amodio","year":"2019"},{"key":"mlstabd614bib1176","first-page":"7167","article-title":"Adversarial discriminative domain adaptation","author":"Tzeng","year":"2017"},{"key":"mlstabd614bib1177","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","author":"Ganin","year":"2015"},{"key":"mlstabd614bib1178","first-page":"4068","article-title":"Simultaneous deep transfer across domains and tasks","author":"Tzeng","year":"2015"},{"key":"mlstabd614bib1179","doi-asserted-by":"publisher","first-page":"1550","DOI":"10.1109\/5.58337","article-title":"Backpropagation through time: what it does and how to do it","volume":"78","author":"Werbos","year":"1990","journal-title":"Proc. IEEE"},{"key":"mlstabd614bib1180","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1109\/TAC.2019.2907172","article-title":"Asymptotic optimality of finite model approximations for partially observed markov decision processes with discounted cost","volume":"65","author":"Saldi","year":"2019","journal-title":"IEEE Trans. Autom. Control"},{"key":"mlstabd614bib1181","first-page":"345","article-title":"Reinforcement learning algorithm for partially observable Markov decision problems","author":"Jaakkola","year":"1995"},{"key":"mlstabd614bib1182","first-page":"2048","article-title":"Show, attend and tell: neural image caption generation with visual attention","author":"Xu","year":"2015"},{"key":"mlstabd614bib1183","first-page":"3156","article-title":"Show and tell: a neural image caption generator","author":"Vinyals","year":"2015"},{"key":"mlstabd614bib1184","first-page":"443","article-title":"Survey on neural machine translation for multilingual translation system","author":"Basmatkar","year":"2019"},{"key":"mlstabd614bib1185","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1093\/jamia\/ocz200","article-title":"Deep learning in clinical natural language processing: a methodical review","volume":"27","author":"Wu","year":"2020","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"mlstabd614bib1186","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979670","article-title":"A survey of the usages of deep learning for natural language processing","author":"Otter","year":"2020","journal-title":"IEEE Trans. on Neural Networks and Learning Systems"},{"key":"mlstabd614bib1187","first-page":"3772","article-title":"Forecasting sparse traffic congestion patterns using message-passing RNNs","author":"Iyer","year":"2020"},{"key":"mlstabd614bib1188","first-page":"495","article-title":"Deep CNN-LSTM with word embeddings for news headline sarcasm detection","author":"Mandal","year":"2019"},{"key":"mlstabd614bib1189","doi-asserted-by":"publisher","first-page":"832","DOI":"10.3390\/make1030048","article-title":"A CNN-BiLSTM model for document-level sentiment analysis","volume":"1","author":"Rhanoui","year":"2019","journal-title":"Machine Learning and Knowledge Extraction"},{"key":"mlstabd614bib1190","doi-asserted-by":"publisher","first-page":"911","DOI":"10.1016\/j.procs.2018.04.221","article-title":"A combination of RNN and CNN for attention-based relation classification","volume":"131","author":"Zhang","year":"2018","journal-title":"Proc. Comput. Sci."},{"key":"mlstabd614bib1191","article-title":"Question answering over freebase via attentive RNN with similarity matrix based CNN","author":"Qu","year":"2018"},{"key":"mlstabd614bib1192","article-title":"From pre-trained word embeddings to pre-trained language models\u2014focus on BERT towards data science","author":"Sieg","year":"2019"},{"key":"mlstabd614bib1193","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"mlstabd614bib1194","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"Mikolov","year":"2013"},{"key":"mlstabd614bib1195","first-page":"2265","article-title":"Learning word embeddings efficiently with noise-contrastive estimation","author":"Mnih","year":"2013"},{"key":"mlstabd614bib1196","article-title":"Learning word vectors for 157 languages","author":"Grave","year":"2018"},{"key":"mlstabd614bib1197","first-page":"1188","article-title":"Distributed representations of sentences and documents","author":"Le","year":"2014"},{"key":"mlstabd614bib1198","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/W16-1609","article-title":"An empirical evaluation of doc2vec with practical insights into document embedding generation","author":"Lau","year":"2016"},{"key":"mlstabd614bib1199","first-page":"1532","article-title":"GloVe: global vectors for word representation","author":"Pennington","year":"2014"},{"key":"mlstabd614bib1200","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013"},{"key":"mlstabd614bib1201","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2019.132306","article-title":"Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network","volume":"404","author":"Sherstinsky","year":"2020","journal-title":"Physica D"},{"key":"mlstabd614bib1202","article-title":"Understanding LSTM networks","author":"Olah","year":"2015"},{"key":"mlstabd614bib1203","doi-asserted-by":"publisher","first-page":"2451","DOI":"10.1162\/089976600300015015","article-title":"Learning to forget: continual prediction with LSTM","volume":"12","author":"Gers","year":"2000","journal-title":"Neural Comput."},{"key":"mlstabd614bib1204","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"mlstabd614bib1205","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/D14-1179","article-title":"Learning phrase representations using rnn encoder\u2013decoder for statistical machine translation","author":"Cho","year":"2014"},{"key":"mlstabd614bib1206","first-page":"1597","article-title":"Gate-variants of gated recurrent unit (GRU) neural networks","author":"Dey","year":"2017"},{"key":"mlstabd614bib1207","first-page":"1593","article-title":"Simplified minimal gated unit variations for recurrent neural networks","author":"Heck","year":"2017"},{"key":"mlstabd614bib1208","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"Pascanu","year":"2013"},{"key":"mlstabd614bib1209","first-page":"582","article-title":"Which neural net architectures give rise to exploding and vanishing gradients?","author":"Hanin","year":"2018"},{"key":"mlstabd614bib1210","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D17-1151","article-title":"Massive exploration of neural machine translation architectures","author":"Britz","year":"2017"},{"key":"mlstabd614bib1211","first-page":"2342","article-title":"An empirical exploration of recurrent network architectures","author":"Jozefowicz","year":"2015"},{"key":"mlstabd614bib1212","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"mlstabd614bib1213","doi-asserted-by":"publisher","first-page":"40","DOI":"10.3389\/frai.2020.00040","article-title":"Are GRU cells more specific and LSTM cells more sensitive in motive classification of text?","volume":"3","author":"Gruber","year":"2020","journal-title":"Frontiers Artif. Intell."},{"key":"mlstabd614bib1214","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P18-2117","article-title":"On the practical computational power of finite precision RNNs for language recognition","author":"Weiss","year":"2018"},{"key":"mlstabd614bib1215","first-page":"755","article-title":"Evolving memory cell structures for sequence learning","author":"Bayer","year":"2009"},{"key":"mlstabd614bib1216","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1007\/s11633-016-1006-2","article-title":"Minimal gated unit for recurrent neural networks","volume":"13","author":"Zhou","year":"2016","journal-title":"Int. J. Autom. Comput."},{"key":"mlstabd614bib1217","doi-asserted-by":"publisher","first-page":"2222","DOI":"10.1109\/TNNLS.2016.2582924","article-title":"LSTM: a search space odyssey","volume":"28","author":"Greff","year":"2016","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"mlstabd614bib1218","article-title":"Discrete event, continuous time RNNs","author":"Mozer","year":"2017"},{"key":"mlstabd614bib1219","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1016\/S0893-6080(05)80125-X","article-title":"Approximation of dynamical systems by continuous time recurrent neural networks","volume":"6","author":"Funahashi","year":"1993","journal-title":"Neural Netw."},{"key":"mlstabd614bib1220","first-page":"357","article-title":"Evolving communication without dedicated communication channels","author":"Quinn","year":"2001"},{"key":"mlstabd614bib1221","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1016\/S0921-8890(96)00063-2","article-title":"The dynamics of adaptive behavior: a research program","volume":"20","author":"Beer","year":"1997","journal-title":"Robot. Auton. Syst."},{"key":"mlstabd614bib1222","doi-asserted-by":"crossref","first-page":"392","DOI":"10.7551\/mitpress\/3117.003.0058","article-title":"Seeing the light: artificial evolution, real vision","volume":"3","author":"Harvey","year":"1994","journal-title":"From Animals Animats"},{"key":"mlstabd614bib1223","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","article-title":"Finding structure in time","volume":"14","author":"Elman","year":"1990","journal-title":"Cogn. Sci."},{"key":"mlstabd614bib1224","first-page":"471","volume":"vol 121","author":"Jordan","year":"1997"},{"key":"mlstabd614bib1225","first-page":"5457","article-title":"Independently recurrent neural network (IndRNN): building a longer and deeper RNN","author":"Li","year":"2018"},{"key":"mlstabd614bib1226","doi-asserted-by":"crossref","DOI":"10.5539\/mas.v2n3p57","article-title":"Logic learning in hopfield networks","author":"Sathasivam","year":"2008"},{"key":"mlstabd614bib1227","article-title":"Recurrent multilayer perceptrons for identification and control: the road to applications","author":"Tutschku","year":"1995"},{"key":"mlstabd614bib1228","article-title":"Long short-term memory projection recurrent neural network architectures for piano\u2019s continuous note recognition","volume":"2017","author":"Jia","year":"2017","journal-title":"J. Robot."},{"key":"mlstabd614bib1229","article-title":"How to construct deep recurrent neural networks","author":"Pascanu","year":"2014"},{"key":"mlstabd614bib1230","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","article-title":"Bidirectional recurrent neural networks","volume":"45","author":"Schuster","year":"1997","journal-title":"IEEE Trans. Signal Process."},{"key":"mlstabd614bib1231","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2015"},{"key":"mlstabd614bib1232","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","article-title":"Framewise phoneme classification with bidirectional lstm and other neural network architectures","volume":"18","author":"Graves","year":"2005","journal-title":"Neural Netw."},{"key":"mlstabd614bib1233","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1109\/tcbb.2007.1015","article-title":"Bidirectional long short-term memory networks for predicting the subcellular localization of eukaryotic proteins","volume":"4","author":"Thireou","year":"2007","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"key":"mlstabd614bib1234","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/W14-4012","article-title":"On the properties of neural machine translation: encoder\u2013decoder approaches","author":"Cho","year":"2014"},{"key":"mlstabd614bib1235","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12047","article-title":"Learning structured representation for text classification via reinforcement learning","author":"Zhang","year":"2018"},{"key":"mlstabd614bib1236","article-title":"Hierarchical multiscale recurrent neural networks","author":"Chung","year":"2016"},{"key":"mlstabd614bib1237","first-page":"553","article-title":"A hierarchical recurrent encoder\u2013decoder for generative context-aware query suggestion","author":"Sordoni","year":"2015"},{"key":"mlstabd614bib1238","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1177\/105971230501300303","article-title":"How hierarchical control self-organizes in artificial adaptive systems","volume":"13","author":"Paine","year":"2005","journal-title":"Adapt. Behav."},{"key":"mlstabd614bib1239","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1162\/neco.1992.4.2.234","article-title":"Learning complex, extended sequences using the principle of history compression","volume":"4","author":"Schmidhuber","year":"1992","journal-title":"Neural Comput."},{"key":"mlstabd614bib1240","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000220","article-title":"Emergence of functional hierarchy in a multiple timescale neural network model: a humanoid robot experiment","volume":"4","author":"Yamashita","year":"2008","journal-title":"PLoS Comput. Biol."},{"key":"mlstabd614bib1241","first-page":"2","article-title":"The hierarchical and functional connectivity of higher-order cognitive mechanisms: neurorobotic model to investigate the stability and flexibility of working memory","volume":"7","author":"Shibata Alnajjar","year":"2013","journal-title":"Frontiers Neurorobot."},{"key":"mlstabd614bib1242","article-title":"An attentive survey of attention models","author":"Chaudhari","year":"2019"},{"key":"mlstabd614bib1243","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D15-1166","article-title":"Effective approaches to attention-based neural machine translation","author":"Luong","year":"2015"},{"key":"mlstabd614bib1244","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014"},{"key":"mlstabd614bib1245","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1038\/nature20101","article-title":"Hybrid computing using a neural network with dynamic external memory","volume":"538","author":"Graves","year":"2016","journal-title":"Nature"},{"key":"mlstabd614bib1246","article-title":"Neural turing machines","author":"Graves","year":"2014"},{"key":"mlstabd614bib1247","article-title":"Recent advances in autoencoder-based representation learning","author":"Tschannen","year":"2018"},{"key":"mlstabd614bib1248","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"Hinton","year":"2006","journal-title":"Science"},{"key":"mlstabd614bib1249","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1002\/aic.690370209","article-title":"Nonlinear principal component analysis using autoassociative neural networks","volume":"37","author":"Kramer","year":"1991","journal-title":"AIChE J."},{"key":"mlstabd614bib1250","article-title":"Is joint training better for deep auto-encoders?","author":"Zhou","year":"2014"},{"key":"mlstabd614bib1251","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2015.0202","article-title":"Principal component analysis: a review and recent developments","volume":"374","author":"Jolliffe","year":"2016","journal-title":"Phil. Trans. R. Soc. A"},{"key":"mlstabd614bib1252","article-title":"Lossy image compression with compressive autoencoders","author":"Theis","year":"2017"},{"key":"mlstabd614bib1253","first-page":"3371","article-title":"Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"Vincent","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"mlstabd614bib1254","first-page":"1096","article-title":"Extracting and composing robust features with denoising autoencoders","author":"Vincent","year":"2008"},{"key":"mlstabd614bib1255","first-page":"241","article-title":"Medical image denoising using convolutional denoising autoencoders","author":"Gondara","year":"2016"},{"key":"mlstabd614bib1256","first-page":"432","article-title":"Simple sparsification improves sparse denoising autoencoders in denoising highly corrupted images","author":"Cho","year":"2013"},{"key":"mlstabd614bib1257","article-title":"Boltzmann machines and denoising autoencoders for image denoising","author":"Cho","year":"2013"},{"key":"mlstabd614bib1258","article-title":"Contractive auto-encoders: explicit invariance during feature extraction","author":"Rifai","year":"2011"},{"key":"mlstabd614bib1259","first-page":"645","article-title":"Higher order contractive auto-encoder","author":"Rifai","year":"2011"},{"key":"mlstabd614bib1260","doi-asserted-by":"crossref","DOI":"10.1561\/9781680836233","article-title":"An introduction to variational autoencoders","author":"Kingma","year":"2019"},{"key":"mlstabd614bib1261","article-title":"Tutorial on variational autoencoders","author":"Doersch","year":"2016"},{"key":"mlstabd614bib1262","article-title":"k-sparse autoencoders","author":"Makhzani","year":"2013"},{"key":"mlstabd614bib1263","first-page":"1339","article-title":"3D object recognition with deep belief nets","author":"Nair","year":"2009"},{"key":"mlstabd614bib1264","first-page":"136","article-title":"Why regularized auto-encoders learn sparse representation?","author":"Arpit","year":"2016"},{"key":"mlstabd614bib1265","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1016\/j.neucom.2017.08.043","article-title":"Facial expression recognition via learning deep sparse autoencoders","volume":"273","author":"Zeng","year":"2018","journal-title":"Neurocomputing"},{"key":"mlstabd614bib1266","doi-asserted-by":"publisher","first-page":"31","DOI":"10.11648\/j.mcs.20200501.14","article-title":"A survey of generative adversarial networks based on encoder\u2013decoder model","volume":"5","author":"Yin","year":"2020","journal-title":"Math. Comput. Sci."},{"key":"mlstabd614bib1267","first-page":"4206","article-title":"VAEGAN: a collaborative filtering framework based on adversarial variational autoencoders","author":"Yu","year":"2019"},{"key":"mlstabd614bib1268","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","author":"Larsen","year":"2016"},{"key":"mlstabd614bib1269","first-page":"4532","article-title":"A new variational method for deep supervised semantic image hashing","author":"Zhuang","year":"2020"},{"key":"mlstabd614bib1270","doi-asserted-by":"publisher","first-page":"1191","DOI":"10.1049\/cje.2019.08.001","article-title":"Deep hashing based on VAE-GAN for efficient similarity retrieval","volume":"28","author":"Jin","year":"2019","journal-title":"Chin. J. Electron."},{"key":"mlstabd614bib1271","article-title":"Model-aware deep architectures for one-bit compressive variational autoencoding","author":"Khobahi","year":"2019"},{"key":"mlstabd614bib1272","first-page":"1453","article-title":"Deep semantic hashing with multi-adversarial training","author":"Wang","year":"2018"},{"key":"mlstabd614bib1273","article-title":"Semantic hashing with variational autoencoders","author":"Patterson","year":"2016"},{"key":"mlstabd614bib1274","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.102920","article-title":"Video anomaly detection and localization via gaussian mixture fully convolutional variational autoencoder","volume":"195","author":"Fan","year":"2020","journal-title":"Comput. Vis. Image Underst."},{"key":"mlstabd614bib1275","first-page":"1","article-title":"Unsupervised anomaly detection using variational auto-encoder based feature extraction","author":"Yao","year":"2019"},{"key":"mlstabd614bib1276","first-page":"187","article-title":"Unsupervised anomaly detection via variational auto-encoder for seasonal KPIs in web applications","author":"Xu","year":"2018"},{"key":"mlstabd614bib1277","first-page":"1","article-title":"Variational autoencoder based anomaly detection using reconstruction probability","volume":"2","author":"An","year":"2015","journal-title":"Spec. Lecture IE"},{"key":"mlstabd614bib1278","first-page":"2103","article-title":"Reverse variational autoencoder for visual attribute manipulation and anomaly detection","author":"Gauerhof","year":"2020"},{"key":"mlstabd614bib1279","first-page":"6444","article-title":"Learning latent subspaces in variational autoencoders","author":"Klys","year":"2018"},{"key":"mlstabd614bib1280","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.trc.2019.07.006","article-title":"How to generate micro-agents? A deep generative modeling approach to population synthesis","volume":"106","author":"Borysov","year":"2019","journal-title":"Transp. Res. C"},{"key":"mlstabd614bib1281","article-title":"Synthetic patient generation: a deep learning approach using variational autoencoders","author":"Salim Jr","year":"2018"},{"key":"mlstabd614bib1282","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1021\/acscentsci.7b00572","article-title":"Automatic chemical design using a data-driven continuous representation of molecules","volume":"4","author":"G\u00f3mez-Bombarelli","year":"2018","journal-title":"ACS Cent. Sci."},{"key":"mlstabd614bib1283","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1038\/s41587-019-0224-x","article-title":"Deep learning enables rapid identification of potent DDR1 kinase inhibitors","volume":"37","author":"Zhavoronkov","year":"2019","journal-title":"Nat. Biotechnol."},{"key":"mlstabd614bib1284","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1039\/C9SC04026A","article-title":"Constrained bayesian optimization for automatic chemical design using variational autoencoders","volume":"11","author":"Griffiths","year":"2020","journal-title":"Chemical Science"},{"key":"mlstabd614bib1285","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-018-0286-7","article-title":"Molecular generative model based on conditional variational autoencoder for de novo molecular design","volume":"10","author":"Lim","year":"2018","journal-title":"J. Cheminform."},{"key":"mlstabd614bib1286","first-page":"1","article-title":"Variational autoencoder based synthetic data generation for imbalanced learning","author":"Wan","year":"2017"},{"key":"mlstabd614bib1287","article-title":"Machine learning testing: survey, landscapes and horizons","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Softw. Eng."},{"key":"mlstabd614bib1288","first-page":"291","article-title":"Software engineering for machine learning: a case study","author":"Amershi","year":"2019"},{"key":"mlstabd614bib1289","first-page":"1123","article-title":"The ML test score: a rubric for ML production readiness and technical debt reduction","author":"Breck","year":"2017"},{"key":"mlstabd614bib1290","first-page":"2503","article-title":"Hidden technical debt in machine learning systems","author":"Sculley","year":"2015"},{"key":"mlstabd614bib1291","article-title":"Loss landscape mit license","author":"Li","year":"2017"},{"key":"mlstabd614bib1292","doi-asserted-by":"crossref","first-page":"321","DOI":"10.54870\/1551-3440.1191","article-title":"A semiotic reflection on the didactics of the chain rule","volume":"7","author":"Rodr\u00edguez","year":"2010","journal-title":"Math. Enthusiast"},{"key":"mlstabd614bib1293","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1214\/aoms\/1177729392","article-title":"Stochastic estimation of the maximum of a regression function","volume":"23","author":"Kiefer","year":"1952","journal-title":"Ann. Math. Stat."},{"key":"mlstabd614bib1294","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","article-title":"A stochastic approximation method","volume":"22","author":"Robbins","year":"1951","journal-title":"Ann. Math. Stat."},{"key":"mlstabd614bib1295","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0041-5553(64)90137-5","article-title":"Some methods of speeding up the convergence of iteration methods","volume":"4","author":"Polyak","year":"1964","journal-title":"USSR Comput. Math. Math. Phys."},{"key":"mlstabd614bib1296","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"Sutskever","year":"2013"},{"key":"mlstabd614bib1297","first-page":"2510","article-title":"A differential equation for modeling Nesterov\u2019s accelerated gradient method: theory and insights","author":"Su","year":"2014"},{"key":"mlstabd614bib1298","article-title":"TensorFlow Source Code for Nesterov Momentum","year":"2018"},{"key":"mlstabd614bib1299","article-title":"Quasi-qyperbolic momentum and ADAM for deep learning","author":"Ma","year":"2018"},{"key":"mlstabd614bib1300","article-title":"Aggregated momentum: stability through passive damping","author":"Lucas","year":"2018"},{"key":"mlstabd614bib1301","article-title":"Neural networks for machine learning lecture 6a overview of mini-batch gradient descent","author":"Hinton","year":"2012"},{"key":"mlstabd614bib1302","article-title":"ADAM: a method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"mlstabd614bib1303","doi-asserted-by":"publisher","first-page":"3668","DOI":"10.1109\/TCYB.2019.2950779","article-title":"A survey of optimization methods from a machine learning perspective","volume":"50","author":"Sun","year":"2019","journal-title":"IEEE Trans. Cybern."},{"key":"mlstabd614bib1304","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1137\/16M1080173","article-title":"Optimization methods for large-scale machine learning","volume":"60","author":"Bottou","year":"2018","journal-title":"SIAM Rev."},{"key":"mlstabd614bib1305","article-title":"An overview of gradient descent optimization algorithms","author":"Ruder","year":"2016"},{"key":"mlstabd614bib1306","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1090\/qam\/10667","article-title":"The method of steepest descent for non-linear minimization problems","volume":"2","author":"Curry","year":"1944","journal-title":"Q. Appl. Math."},{"key":"mlstabd614bib1307","first-page":"254","article-title":"Cauchy and the gradient method","volume":"251","author":"Lemar\u00e9chal","year":"2012","journal-title":"Doc. Math. Extra"},{"key":"mlstabd614bib1308","article-title":"Training deep nets with sublinear memory cost","author":"Chen","year":"2016"},{"key":"mlstabd614bib1309","article-title":"Saving memory using gradient-checkpointing","author":"","year":"2019"},{"key":"mlstabd614bib1310","article-title":"Spatially parallel convolutions","author":"Jin","year":"2018"},{"key":"mlstabd614bib1311","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1016\/j.tics.2018.12.005","article-title":"Theories of error back-propagation in the brain","volume":"23","author":"Whittington","year":"2019","journal-title":"Trends Cogn. Sci."},{"key":"mlstabd614bib1312","doi-asserted-by":"publisher","first-page":"692","DOI":"10.1037\/a0014345","article-title":"Exercising your brain: a review of human brain plasticity and training-induced learning","volume":"23","author":"Green","year":"2008","journal-title":"Psychol. Aging"},{"key":"mlstabd614bib1313","doi-asserted-by":"publisher","first-page":"7641","DOI":"10.1073\/pnas.1018985108","article-title":"Dynamic reconfiguration of human brain networks during learning","volume":"108","author":"Bassett","year":"2011","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstabd614bib1314","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1016\/j.conb.2004.10.016","article-title":"Reward representations and reward-related learning in the human brain: insights from neuroimaging","volume":"14","author":"O\u2019Doherty","year":"2004","journal-title":"Curr. Opin. Neurobiol."},{"key":"mlstabd614bib1315","article-title":"Adaptive gradient methods with dynamic bound of learning rate","author":"Luo","year":"2019"},{"key":"mlstabd614bib1316","article-title":"On the convergence of ADAM and beyond","author":"Reddi","year":"2019"},{"key":"mlstabd614bib1317","first-page":"9597","article-title":"Lookahead optimizer: k steps forward, 1 step back","author":"Zhang","year":"2019"},{"key":"mlstabd614bib1318","article-title":"Incorporating Nesterov momentum into ADAM","author":"Dozat","year":"2016"},{"key":"mlstabd614bib1319","article-title":"Nostalgic Adam: weighting more of the past gradients when designing the adaptive learning rate","author":"Huang","year":"2018"},{"key":"mlstabd614bib1320","article-title":"Power gradient descent","author":"Baiesi","year":"2019"},{"key":"mlstabd614bib1321","article-title":"On the variance of the adaptive learning rate and beyond","author":"Liu","year":"2019"},{"key":"mlstabd614bib1322","article-title":"Neural optimizer search with reinforcement learning","author":"Bello","year":"2017"},{"key":"mlstabd614bib1323","first-page":"3981","article-title":"Learning to learn by gradient descent by gradient descent","author":"Andrychowicz","year":"2016"},{"key":"mlstabd614bib1324","article-title":"Learning to optimize","author":"Li","year":"2016"},{"key":"mlstabd614bib1325","first-page":"87","article-title":"Learning to learn using gradient descent","author":"Hochreiter","year":"2001"},{"key":"mlstabd614bib1326","article-title":"RL2: fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016"},{"key":"mlstabd614bib1327","article-title":"Stochastic gradient descent optimizes over-parameterized deep ReLU networks","author":"Zou","year":"2018"},{"key":"mlstabd614bib1328","article-title":"Two natural weaknesses of gradient descent","author":"Watt","year":"2020"},{"key":"mlstabd614bib1329","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00006","article-title":"Why momentum really works","author":"Goh","year":"2017","journal-title":"Distill"},{"key":"mlstabd614bib1330","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/S0893-6080(98)00116-6","article-title":"On the momentum term in gradient descent learning algorithms","volume":"12","author":"Qian","year":"1999","journal-title":"Neural Netw."},{"key":"mlstabd614bib1331","article-title":"Descending through a crowded valley\u2014benchmarking deep learning optimizers","author":"Schmidt","year":"2020"},{"key":"mlstabd614bib1332","article-title":"On empirical comparisons of optimizers for deep learning","author":"Choi","year":"2019"},{"key":"mlstabd614bib1333","first-page":"4148","article-title":"The marginal value of adaptive gradient methods in machine learning","author":"Wilson","year":"2017"},{"key":"mlstabd614bib1334","first-page":"92","article-title":"A comparative analysis of gradient descent-based optimization algorithms on convolutional neural networks","author":"Dogo","year":"2018"},{"key":"mlstabd614bib1335","doi-asserted-by":"crossref","DOI":"10.1109\/MLSP49062.2020.9231926","article-title":"AutoClip: adaptive gradient clipping for source separation networks","author":"Seetharaman","year":"2020"},{"key":"mlstabd614bib1336","article-title":"Stochastic optimization with heavy-tailed noise via accelerated gradient clipping","author":"Gorbunov","year":"2020"},{"key":"mlstabd614bib1337","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-020-14645-x","article-title":"Natural images are reliably represented by sparse and variable populations of neurons in visual cortex","volume":"11","author":"Yoshida","year":"2020","journal-title":"Nat. Commun."},{"key":"mlstabd614bib1338","article-title":"Tunability: importance of hyperparameters of machine learning algorithms","author":"Probst","year":"2018"},{"key":"mlstabd614bib1339","article-title":"The step decay schedule: a near optimal, geometrically decaying learning rate procedure","author":"Ge","year":"2019"},{"key":"mlstabd614bib1340","article-title":"Decaying momentum helps neural network training","author":"Chen","year":"2019"},{"key":"mlstabd614bib1341","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2020.07.061","article-title":"On hyperparameter optimization of machine learning algorithms: theory and practice","author":"Yang","year":"2020"},{"key":"mlstabd614bib1342","article-title":"Gradient descent: the ultimate optimizer","author":"Chandra","year":"2019"},{"key":"mlstabd614bib1343","first-page":"2623","article-title":"Optuna: a next-generation hyperparameter optimization framework","author":"Akiba","year":"2019"},{"key":"mlstabd614bib1344","article-title":"HyperNOMAD: hyperparameter optimization of deep neural networks using mesh adaptive direct search","author":"Lakhmiri","year":"2019"},{"key":"mlstabd614bib1345","first-page":"822","article-title":"Efficient hyperparameter optimization of deep learning algorithms using deterministic RBF surrogates","author":"Ilievski","year":"2017"},{"key":"mlstabd614bib1346","first-page":"481","article-title":"Particle swarm optimization for hyper-parameter selection in deep neural networks","author":"Lorenzo","year":"2017"},{"key":"mlstabd614bib1347","doi-asserted-by":"publisher","first-page":"1793","DOI":"10.1109\/TNN.2010.2073482","article-title":"Neural network learning without backpropagation","volume":"21","author":"Wilamowski","year":"2010","journal-title":"IEEE Trans. Neural Netw."},{"key":"mlstabd614bib1348","article-title":"Learning complexity of simulated annealing","author":"Blum","year":"2020"},{"key":"mlstabd614bib1349","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/0895-7177(93)90204-C","article-title":"Simulated annealing: practice versus theory","volume":"18","author":"Ingber","year":"1993","journal-title":"Math. Comput. Modelling"},{"key":"mlstabd614bib1350","first-page":"506","article-title":"Optimization of convolutional neural network using microcanonical annealing algorithm","author":"Ayumi","year":"2016"},{"key":"mlstabd614bib1351","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.procs.2015.12.114","article-title":"Simulated annealing algorithm for deep learning","volume":"72","author":"Rere","year":"2015","journal-title":"Proc. Comput. Sci."},{"key":"mlstabd614bib1352","article-title":"CoolMomentum: a method for stochastic optimization by langevin dynamics with simulated annealing","author":"Borysenko","year":"2020"},{"key":"mlstabd614bib1353","article-title":"Embedded hyper-parameter tuning by simulated annealing","author":"Fischetti","year":"2019"},{"key":"mlstabd614bib1354","first-page":"307","author":"Sloss","year":"2020"},{"key":"mlstabd614bib1355","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1080\/03036758.2019.1609052","article-title":"A survey on evolutionary machine learning","volume":"49","author":"Al-Sahaf","year":"2019","journal-title":"J. R. Soc. New Zealand"},{"key":"mlstabd614bib1356","first-page":"146","author":"Shapiro","year":"1999"},{"key":"mlstabd614bib1357","first-page":"777","article-title":"Fast genetic algorithms","author":"Doerr","year":"2017"},{"key":"mlstabd614bib1358","article-title":"Deep neuroevolution: genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning","author":"Such","year":"2017"},{"key":"mlstabd614bib1359","first-page":"596","article-title":"Deep reinforcement learning using genetic algorithm for parameter optimization","author":"Sehgal","year":"2019"},{"key":"mlstabd614bib1360","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/j.mattod.2020.03.004","article-title":"Genetic algorithm-guided deep learning of grain boundary diagrams: addressing the challenge of five degrees of freedom","volume":"38","author":"Hu","year":"2020","journal-title":"Mater. Today"},{"key":"mlstabd614bib1361","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41524-019-0181-4","article-title":"Genetic algorithms for computational materials discovery accelerated by machine learning","volume":"5","author":"Jennings","year":"2019","journal-title":"npj Comput. Mater."},{"key":"mlstabd614bib1362","article-title":"Augmenting genetic algorithms with deep neural networks for exploring the chemical space","author":"Nigam","year":"2019"},{"key":"mlstabd614bib1363","first-page":"101","article-title":"Genetic algorithms with DNN-based trainable crossover as an example of partial specialization of general search","author":"Potapov","year":"2017"},{"key":"mlstabd614bib1364","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1017\/S0962492900002841","article-title":"Direct search algorithms for optimization calculations","volume":"7","author":"Powell","year":"1998","journal-title":"Numer."},{"key":"mlstabd614bib1365","article-title":"A new backpropagation algorithm without gradient descent","author":"Ranganathan","year":"2018"},{"key":"mlstabd614bib1366","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.swevo.2019.05.010","article-title":"Particle swarm optimization of deep neural networks architectures for image classification","volume":"49","author":"Junior","year":"2019","journal-title":"Swarm Evolutionary Comput."},{"key":"mlstabd614bib1367","first-page":"1285","article-title":"Parameters optimization of deep learning models using particle swarm optimization","author":"Qolomany","year":"2017"},{"key":"mlstabd614bib1368","first-page":"1942","article-title":"Particle swarm optimization","volume":"vol 4","author":"Kennedy","year":"1995"},{"key":"mlstabd614bib1369","first-page":"303","article-title":"The particle swarm: social adaptation of knowledge","author":"Kennedy","year":"1997"},{"key":"mlstabd614bib1370","article-title":"A review of machine learning with echo state networks","author":"Xu","year":"2020"},{"key":"mlstabd614bib1371","doi-asserted-by":"publisher","first-page":"2330","DOI":"10.4249\/scholarpedia.2330","article-title":"Echo state network","volume":"2","author":"Jaeger","year":"2007","journal-title":"Scholarpedia"},{"key":"mlstabd614bib1372","article-title":"Deep echo state network (DeepESN): a brief survey","author":"Gallicchio","year":"2017"},{"key":"mlstabd614bib1373","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.neucom.2019.03.086","article-title":"Towards a more efficient and cost-sensitive extreme learning machine: a state-of-the-art review of recent trend","volume":"350","author":"Alaba","year":"2019","journal-title":"Neurocomputing"},{"key":"mlstabd614bib1374","first-page":"572","article-title":"A survey on extreme learning machine and evolution of its variants","author":"Ghosh","year":"2018"},{"key":"mlstabd614bib1375","first-page":"4610","article-title":"Extreme learning machine: a review","volume":"12","author":"Albadra","year":"2017","journal-title":"Int. J. Appl. Eng. Res."},{"key":"mlstabd614bib1376","doi-asserted-by":"publisher","first-page":"809","DOI":"10.1109\/TNNLS.2015.2424995","article-title":"Extreme learning machine for multilayer perceptron","volume":"27","author":"Tang","year":"2015","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"mlstabd614bib1377","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1109\/TSMCB.2011.2168604","article-title":"Extreme learning machine for regression and multiclass classification","volume":"42","author":"Huang","year":"2011","journal-title":"IEEE Trans. Syst. Man Cybern. B"},{"key":"mlstabd614bib1378","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.neucom.2005.12.126","article-title":"Extreme learning machine: theory and applications","volume":"70","author":"Huang","year":"2006","journal-title":"Neurocomputing"},{"key":"mlstabd614bib1379","first-page":"985","article-title":"Extreme learning machine: a new learning scheme of feedforward neural networks","volume":"vol 2","author":"Huang","year":"2004"},{"key":"mlstabd614bib1380","article-title":"Deep reinforcement learning: an overview","author":"Li","year":"2017"},{"key":"mlstabd614bib1381","article-title":"A survey of reinforcement learning techniques: strategies, recent development, and future directions","author":"Mondal","year":"2020"},{"key":"mlstabd614bib1382","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.3570254","article-title":"Deep reinforcement learning patents: an empirical survey","author":"Haney","year":"2020"},{"key":"mlstabd614bib1383","doi-asserted-by":"publisher","first-page":"3826","DOI":"10.1109\/TCYB.2020.2977374","article-title":"Deep reinforcement learning for multiagent systems: a review of challenges, solutions and applications","volume":"50","author":"Nguyen","year":"2020","journal-title":"IEEE Trans. Cybern."},{"key":"mlstabd614bib1384","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1016\/j.tics.2019.02.006","article-title":"Reinforcement learning, fast and slow","volume":"23","author":"Botvinick","year":"2019","journal-title":"Trends Cogn. Sci."},{"key":"mlstabd614bib1385","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1146\/annurev-control-053018-023825","article-title":"A tour of reinforcement learning: the view from continuous control","volume":"2","author":"Recht","year":"2019","journal-title":"Annu. Rev. Control Robot. Auton. Syst."},{"key":"mlstabd614bib1386","doi-asserted-by":"crossref","DOI":"10.1109\/MSP.2017.2743240","article-title":"A brief survey of deep reinforcement learning","author":"Arulkumaran","year":"2017"},{"key":"mlstabd614bib1387","article-title":"Deep reinforcement learning for autonomous driving: a survey","author":"Kiran","year":"2020"},{"key":"mlstabd614bib1388","first-page":"2326","article-title":"Autonomous highway driving using deep reinforcement learning","author":"Nageshrao","year":"2019"},{"key":"mlstabd614bib1389","doi-asserted-by":"crossref","DOI":"10.5220\/0007520305640572","article-title":"Exploring applications of deep reinforcement learning for real-world autonomous driving systems","author":"Talpaert","year":"2019"},{"key":"mlstabd614bib1390","doi-asserted-by":"publisher","first-page":"3133","DOI":"10.1109\/COMST.2019.2916583","article-title":"Applications of deep reinforcement learning in communications and networking: a survey","volume":"21","author":"Luong","year":"2019","journal-title":"IEEE Commun. Surv. Tutorials"},{"key":"mlstabd614bib1391","first-page":"1","author":"Di Felice","year":"2018"},{"key":"mlstabd614bib1392","doi-asserted-by":"publisher","DOI":"10.1016\/j.scs.2019.101748","article-title":"A review of reinforcement learning methodologies for controlling occupant comfort in buildings","volume":"51","author":"Han","year":"2019","journal-title":"Sustain. Cities Soc."},{"key":"mlstabd614bib1393","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1016\/j.compeleceng.2019.07.019","article-title":"A review of reinforcement learning for autonomous building energy management","volume":"78","author":"Mason","year":"2019","journal-title":"Comput. Electr. Eng."},{"key":"mlstabd614bib1394","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"mlstabd614bib1395","first-page":"590","article-title":"Review of deep reinforcement learning for robot manipulation","author":"Nguyen","year":"2019"},{"key":"mlstabd614bib1396","doi-asserted-by":"publisher","first-page":"4","DOI":"10.3390\/robotics8010004","article-title":"Deep reinforcement learning for soft, flexible robots: brief review with impending challenges","volume":"8","author":"Bhagat","year":"2019","journal-title":"Robotics"},{"key":"mlstabd614bib1397","first-page":"262","article-title":"Analysis and improvement of policy gradient estimation","author":"Zhao","year":"2011"},{"key":"mlstabd614bib1398","article-title":"Exploration strategies in deep reinforcement learning","author":"Weng","year":"2020"},{"key":"mlstabd614bib1399","article-title":"Parameter space noise for exploration","author":"Plappert","year":"2018"},{"key":"mlstabd614bib1400","doi-asserted-by":"publisher","first-page":"823","DOI":"10.1103\/PhysRev.36.823","article-title":"On the theory of the brownian motion","volume":"36","author":"Uhlenbeck","year":"1930","journal-title":"Phys. Rev."},{"key":"mlstabd614bib1401","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"},{"key":"mlstabd614bib1402","article-title":"Distributed distributional deterministic policy gradients","author":"Barth-Maron","year":"2018"},{"key":"mlstabd614bib1403","article-title":"Has it explored enough?","author":"Kosaka","year":"2019"},{"key":"mlstabd614bib1404","article-title":"Noisy networks for exploration","author":"Fortunato","year":"2019"},{"key":"mlstabd614bib1405","first-page":"2681","article-title":"Provably efficient maximum entropy exploration","author":"Hazan","year":"2019"},{"key":"mlstabd614bib1406","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume":"vol 70","author":"Haarnoja","year":"2017"},{"key":"mlstabd614bib1407","first-page":"151","article-title":"Understanding the impact of entropy on policy optimization","author":"Ahmed","year":"2019"},{"key":"mlstabd614bib1408","article-title":"A survey on intrinsic motivation in reinforcement learning","author":"Aubret","year":"2019"},{"key":"mlstabd614bib1409","article-title":"Adapting behaviour via intrinsic reward: a survey and empirical study","author":"Linke","year":"2019"},{"key":"mlstabd614bib1410","first-page":"16","article-title":"Curiosity-driven exploration by self- supervised prediction","author":"Pathak","year":"2017"},{"key":"mlstabd614bib1411","article-title":"Online learning: a comprehensive survey","author":"Hoi","year":"2018"},{"key":"mlstabd614bib1412","first-page":"4987","article-title":"Online reinforcement learning in stochastic games","author":"Wei","year":"2017"},{"key":"mlstabd614bib1413","article-title":"Offline reinforcement learning: tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"mlstabd614bib1414","author":"Seita","year":"2020"},{"key":"mlstabd614bib1415","article-title":"Revisiting fundamentals of experience replay","author":"Fedus","year":"2020"},{"key":"mlstabd614bib1416","article-title":"Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020"},{"key":"mlstabd614bib1417","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/BF00992699","article-title":"Self-improving reactive agents based on reinforcement learning, planning and teaching","volume":"8","author":"Lin","year":"1992","journal-title":"Mach. Learn."},{"key":"mlstabd614bib1418","article-title":"A deeper look at experience replay","author":"Zhang","year":"2017"},{"key":"mlstabd614bib1419","article-title":"AutoML: a survey of the state-of-the-art","author":"He","year":"2019"},{"key":"mlstabd614bib1420","article-title":"Modeling neural architecture search methods for deep networks","author":"Malekhosseini","year":"2019"},{"key":"mlstabd614bib1421","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.imavis.2019.06.005","article-title":"Reinforcement learning for neural architecture search: a review","volume":"89","author":"Jaafra","year":"2019","journal-title":"Image Vis. Comput."},{"key":"mlstabd614bib1422","article-title":"Neural architecture search: a survey","author":"Elsken","year":"2018"},{"key":"mlstabd614bib1423","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101822","article-title":"Automated machine learning: review of the state-of-the-art and opportunities for healthcare","volume":"104","author":"Waring","year":"2020","journal-title":"Artif. Intell. Med."},{"key":"mlstabd614bib1424","article-title":"AdaNet: a scalable and flexible framework for automatically learning ensembles","author":"Weill","year":"2019"},{"key":"mlstabd614bib1425","article-title":"Introducing AdaNet: fast and flexible AutoML with learning guarantees google AI blog","author":"Weill","year":"2018"},{"key":"mlstabd614bib1426","first-page":"82","article-title":"Auto-DeepLab: hierarchical neural architecture search for semantic image segmentation","author":"Liu","year":"2019"},{"key":"mlstabd614bib1427","first-page":"3224","article-title":"AutoGAN: neural architecture search for generative adversarial networks","author":"Gong","year":"2019"},{"key":"mlstabd614bib1428","first-page":"1946","article-title":"Auto-Keras: an efficient neural architecture search system","author":"Jin","year":"2019"},{"key":"mlstabd614bib1429","first-page":"2962","article-title":"Efficient and robust automated machine learning","author":"Feurer","year":"2015"},{"key":"mlstabd614bib1430","article-title":"DARTS+: improved differentiable architecture search with early stopping","author":"Liang","year":"2019"},{"key":"mlstabd614bib1431","article-title":"H2O AutoML: scalable automatic machine learning","volume":"vol 2020","author":"LeDell","year":"2020"},{"key":"mlstabd614bib1432","article-title":"Ludwig: a type-based declarative deep learning toolbox","author":"Molino","year":"2019"},{"key":"mlstabd614bib1433","first-page":"1","article-title":"Optimizing deep learning hyper-parameters through an evolutionary algorithm","author":"Young","year":"2015"},{"key":"mlstabd614bib1434","first-page":"638","article-title":"167-PFLOPS deep learning for electron microscopy: from learning physics to atomic manipulation","author":"Patton","year":"2018"},{"key":"mlstabd614bib1435","first-page":"2016","article-title":"Neural architecture search with bayesian optimisation and optimal transport","author":"Kandasamy","year":"2018"},{"key":"mlstabd614bib1436","first-page":"1977","article-title":"XNAS: neural architecture search with expert advice","author":"Nayman","year":"2019"},{"key":"mlstabd614bib1437","first-page":"1","article-title":"Accuracy vs. efficiency: achieving both through FPGA-implementation aware neural architecture search","author":"Jiang","year":"2019"},{"key":"mlstabd614bib1438","first-page":"19","article-title":"Progressive neural architecture search","author":"Liu","year":"2018"},{"key":"mlstabd614bib1439","article-title":"Graph hypernetworks for neural architecture search","author":"Zhang","year":"2018"},{"key":"mlstabd614bib1440","article-title":"Accelerating neural architecture search using performance prediction","author":"Baker","year":"2017"},{"key":"mlstabd614bib1441","article-title":"Neural architecture search with reinforcement learning","author":"Zoph","year":"2016"},{"key":"mlstabd614bib1442","doi-asserted-by":"crossref","DOI":"10.1145\/3448326.3448353","article-title":"Can AutoML outperform humans? An evaluation on popular OpenML datasets using AutoML benchmark","author":"Hanussek","year":"2020"},{"key":"mlstabd614bib1443","article-title":"Hyper-parameters in action! Part II\u2014weight initializers towards data science","author":"Godoy","year":"2018"},{"key":"mlstabd614bib1444","article-title":"Generalization in deep networks: the role of distance from initialization","author":"Nagarajan","year":"2019"},{"key":"mlstabd614bib1445","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"Glorot","year":"2010"},{"key":"mlstabd614bib1446","article-title":"On weight initialization in deep neural networks","author":"Kumar","year":"2017"},{"key":"mlstabd614bib1447","article-title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","author":"Saxe","year":"2013"},{"key":"mlstabd614bib1448","article-title":"Recurrent orthogonal networks and long-memory tasks","author":"Henaff","year":"2016"},{"key":"mlstabd614bib1449","article-title":"A simple way to initialize recurrent networks of rectified linear units","author":"Le","year":"2015"},{"key":"mlstabd614bib1450","article-title":"Learning longer memory in recurrent neural networks","author":"Mikolov","year":"2014"},{"key":"mlstabd614bib1451","article-title":"Non-zero initial states for recurrent neural networks","author":"Pitis","year":"2016"},{"key":"mlstabd614bib1452","article-title":"All you need is a good init","author":"Mishkin","year":"2015"},{"key":"mlstabd614bib1453","article-title":"Random walk initialization for training very deep feedforward networks","author":"Sussillo","year":"2014"},{"key":"mlstabd614bib1454","first-page":"12645","article-title":"MetaInit: initializing learning by learning to initialize","author":"Dauphin","year":"2019"},{"key":"mlstabd614bib1455","article-title":"Regularization for deep learning: a taxonomy","author":"Kuka\u010dka","year":"2017"},{"key":"mlstabd614bib1456","article-title":"Regularization in deep neural networks","author":"Kang","year":"2019"},{"key":"mlstabd614bib1457","article-title":"Regularization matters in policy optimization","author":"Liu","year":"2019"},{"key":"mlstabd614bib1458","article-title":"Regularized deep learning with non-convex penalties","author":"Vettam","year":"2019"},{"key":"mlstabd614bib1459","first-page":"10678","article-title":"Time matters in regularizing deep networks: weight decay and data augmentation affect early learning dynamics, matter little near convergence","author":"Golatkar","year":"2019"},{"key":"mlstabd614bib1460","article-title":"A new angle on L2 regularization","author":"Tanay","year":"2018"},{"key":"mlstabd614bib1461","article-title":"L2 regularization versus batch and weight normalization","author":"Van Laarhoven","year":"2017"},{"key":"mlstabd614bib1462","first-page":"181","article-title":"The lost honour of L2-based regularization","volume":"13","author":"Van Den Doel","year":"2012","journal-title":"Large Scale Inverse Problems"},{"key":"mlstabd614bib1463","doi-asserted-by":"publisher","first-page":"5016","DOI":"10.1109\/TIT.2012.2197174","article-title":"Compressible distributions for high-dimensional statistics","volume":"58","author":"Gribonval","year":"2012","journal-title":"IEEE Trans. Inf. Theory"},{"key":"mlstabd614bib1464","first-page":"p 78","article-title":"Feature selection, L1 vs. L2 regularization and rotational invariance","author":"Ng","year":"2004"},{"key":"mlstabd614bib1465","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","article-title":"Regularization and variable selection via the elastic net","volume":"67","author":"Zou","year":"2005","journal-title":"J. R. Stat. Soc. B"},{"key":"mlstabd614bib1466","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J. R. Stat. Soc. B"},{"key":"mlstabd614bib1467","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1080\/00401706.1970.10488634","article-title":"Ridge regression: biased estimation for nonorthogonal problems","volume":"12","author":"Hoerl","year":"1970","journal-title":"Technometrics"},{"key":"mlstabd614bib1468","article-title":"Why gradient clipping accelerates training: a theoretical justification for adaptivity","author":"Zhang","year":"2019"},{"key":"mlstabd614bib1469","article-title":"Understanding gradient clipping in private SGD: a geometric perspective","author":"Chen","year":"2020"},{"key":"mlstabd614bib1470","article-title":"Can gradient clipping mitigate label noise?","author":"Menon","year":"2019"},{"key":"mlstabd614bib1471","first-page":"8624","article-title":"Advances in optimizing recurrent networks","author":"Bengio","year":"2013"},{"key":"mlstabd614bib1472","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P18-1008","article-title":"The best of both worlds: combining recent advances in neural machine translation","author":"Chen","year":"2018"},{"key":"mlstabd614bib1473","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"mlstabd614bib1474","article-title":"Survey of dropout methods for deep neural networks","author":"Labach","year":"2019"},{"key":"mlstabd614bib1475","first-page":"2523","article-title":"Improved dropout for shallow and deep learning","author":"Li","year":"2016"},{"key":"mlstabd614bib1476","first-page":"3540","article-title":"On the implicit bias of dropout","author":"Mianjy","year":"2018"},{"key":"mlstabd614bib1477","article-title":"An empirical analysis of dropout in piecewise linear networks","author":"Warde-Farley","year":"2013"},{"key":"mlstabd614bib1478","doi-asserted-by":"crossref","first-page":"12777","DOI":"10.1007\/s11042-019-08453-9","article-title":"Dropout vs. batch normalization: an empirical study of their impact to deep learning","volume":"79","author":"Garbin","year":"2020","journal-title":"Multimedia Tools Appl."},{"key":"mlstabd614bib1479","article-title":"Effective and efficient dropout for deep convolutional neural networks","author":"Cai","year":"2019"},{"key":"mlstabd614bib1480","first-page":"10727","article-title":"DropBlock: a regularization method for convolutional networks","author":"Ghiasi","year":"2018"},{"key":"mlstabd614bib1481","article-title":"PatchUp: a regularization technique for convolutional neural networks","author":"Faramarzi","year":"2020"},{"key":"mlstabd614bib1482","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1109\/TPAMI.2017.2701831","article-title":"Shakeout: a new approach to regularized deep neural network training","volume":"40","author":"Kang","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstabd614bib1483","first-page":"1751","article-title":"Shakeout: a new regularized deep neural network training scheme","author":"Kang","year":"2016"},{"key":"mlstabd614bib1484","article-title":"Towards understanding the importance of noise in training neural networks","author":"Zhou","year":"2019"},{"key":"mlstabd614bib1485","first-page":"6645","article-title":"Speech recognition with deep recurrent neural networks","author":"Graves","year":"2013"},{"key":"mlstabd614bib1486","first-page":"2348","article-title":"Practical variational inference for neural networks","author":"Graves","year":"2011"},{"key":"mlstabd614bib1487","doi-asserted-by":"publisher","first-page":"2227","DOI":"10.1109\/TNNLS.2019.2927689","article-title":"A limitation of gradient descent learning","volume":"31","author":"Sum","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"mlstabd614bib1488","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1109\/72.105415","article-title":"Using additive noise in back-propagation training","volume":"3","author":"Holmstrom","year":"1992","journal-title":"IEEE Trans. Neural Netw."},{"key":"mlstabd614bib1489","first-page":"909","article-title":"Adversarial noise layer: regularize neural network by adding noise","author":"You","year":"2019"},{"key":"mlstabd614bib1490","first-page":"12145","article-title":"On stabilizing generative adversarial training with noise","author":"Jenni","year":"2019"},{"key":"mlstabd614bib1491","doi-asserted-by":"publisher","first-page":"168296","DOI":"10.1109\/ACCESS.2019.2954547","article-title":"Limited gradient descent: learning with noisy labels","volume":"7","author":"Sun","year":"2019","journal-title":"IEEE Access"},{"key":"mlstabd614bib1492","article-title":"A tail-index analysis of stochastic gradient noise in deep neural networks","author":"Simsekli","year":"2019"},{"key":"mlstabd614bib1493","article-title":"Adding gradient noise improves learning for very deep networks","author":"Neelakantan","year":"2015"},{"key":"mlstabd614bib1494","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"Shorten","year":"2019","journal-title":"Journal of Big Data"},{"key":"mlstabd614bib1495","article-title":"Automatic data augmentation for generalization in deep reinforcement learning","author":"Raileanu","year":"2020"},{"key":"mlstabd614bib1496","doi-asserted-by":"crossref","article-title":"On regularization properties of artificial datasets for deep learning","author":"Antczak","DOI":"10.5604\/01.3001.0013.6599"},{"key":"mlstabd614bib1497","article-title":"An overview of deep semi-supervised learning","author":"Ouali","year":"2020"},{"key":"mlstabd614bib1498","article-title":"Semi-supervised learning: the case when unlabeled data is equally useful","author":"Zhu","year":"2020"},{"key":"mlstabd614bib1499","article-title":"A statistical theory of semi-supervised learning","author":"Aitchison","year":"2020"},{"key":"mlstabd614bib1500","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/s42044-018-00027-6","article-title":"A review of various semi-supervised learning models with a deep learning and memory approach","volume":"2","author":"Bagherzadeh","year":"2019","journal-title":"Iran J. Comput. Sci."},{"key":"mlstabd614bib1501","first-page":"3546","article-title":"Semi-supervised learning with ladder networks","author":"Rasmus","year":"2015"},{"key":"mlstabd614bib1502","article-title":"Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks","volume":"vol 3","author":"Lee","year":"2013"},{"key":"mlstabd614bib1503","first-page":"85","author":"Sun","year":"2019"},{"key":"mlstabd614bib1504","article-title":"An overview of multi-task learning in deep neural networks","author":"Ruder","year":"2017"},{"key":"mlstabd614bib1505","doi-asserted-by":"publisher","first-page":"29705","DOI":"10.1007\/s11042-018-6463-x","article-title":"A brief review on multi-task learning","volume":"77","author":"Thung","year":"2018","journal-title":"Multimedia Tools Appl."},{"key":"mlstabd614bib1506","article-title":"A survey on multi-task learning","author":"Zhang","year":"2017"},{"key":"mlstabd614bib1507","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007379606734","article-title":"Multitask learning","volume":"28","author":"Caruana","year":"1997","journal-title":"Mach. Learn."},{"key":"mlstabd614bib1508","article-title":"Conditional image synthesis with auxiliary classifier GANs","author":"Odena","year":"2016"},{"key":"mlstabd614bib1509","article-title":"AC-GAN learns a biased distribution","volume":"vol 8","author":"Shu","year":"2017"},{"key":"mlstabd614bib1510","first-page":"1330","article-title":"Twin auxilary classifiers GAN","author":"Gong","year":"2019"},{"key":"mlstabd614bib1511","article-title":"Unbiased auxiliary classifier GANs with MINE","author":"Han","year":"2020"},{"key":"mlstabd614bib1512","author":"","year":"2020"},{"key":"mlstabd614bib1513","article-title":"On feature normalization and data augmentation","author":"Li","year":"2020"},{"key":"mlstabd614bib1514","article-title":"Impact of data normalization on deep neural network for time series forecasting","author":"Bhanja","year":"2018"},{"key":"mlstabd614bib1515","first-page":"4287","article-title":"Learning values across many orders of magnitude","author":"van Hasselt","year":"2016"},{"key":"mlstabd614bib1516","first-page":"4313","article-title":"Gradient descent with early stopping is provably robust to label noise for overparameterized neural networks","author":"Li","year":"2020"},{"key":"mlstabd614bib1517","article-title":"Bounding the expected run-time of nonconvex optimization with early stopping","author":"Flynn","year":"2020"},{"key":"mlstabd614bib1518","first-page":"4703","article-title":"SGD without replacement: sharper rates for general smooth convex functions","author":"Nagaraj","year":"2019"},{"key":"mlstabd614bib1519","article-title":"Why random reshuffling beats stochastic gradient descent","author":"G\u00fcrb\u00fczbalaban","year":"2019","journal-title":"Math. Program."},{"key":"mlstabd614bib1520","first-page":"2624","article-title":"Random shuffling beats SGD after finite epochs","author":"Haochen","year":"2019"},{"key":"mlstabd614bib1521","first-page":"46","article-title":"Without-replacement sampling for stochastic gradient methods","author":"Shamir","year":"2016"},{"key":"mlstabd614bib1522","article-title":"Curiously fast convergence of some stochastic gradient descent algorithms","author":"Bottou","year":"2009"},{"key":"mlstabd614bib1523","author":"","year":"2020"},{"key":"mlstabd614bib1524","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1080\/10408347.2017.1361314","article-title":"Multiple versus single set validation of multivariate models to avoid mistakes","volume":"48","author":"Harrington","year":"2018","journal-title":"Crit. Rev. Anal. Chem."},{"key":"mlstabd614bib1525","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/BF00058655","article-title":"Bagging predictors","volume":"24","author":"Breiman","year":"1996","journal-title":"Mach. Learn."},{"key":"mlstabd614bib1526","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"mlstabd614bib1527","doi-asserted-by":"publisher","first-page":"251","DOI":"10.23956\/ijarcsse\/V7I1\/01113","article-title":"Random forest: a review","volume":"7","author":"Goel","year":"2017","journal-title":"Int. J. Adv. Res. Comput. Sci. Softw. Eng."},{"key":"mlstabd614bib1528","doi-asserted-by":"publisher","first-page":"e1301","DOI":"10.1002\/widm.1301","article-title":"Hyperparameters and tuning strategies for random forest","volume":"9","author":"Probst","year":"2019","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"mlstabd614bib1529","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/s41664-018-0068-2","article-title":"On splitting training and validation set: a comparative study of cross-validation, bootstrap and systematic sampling for estimating the generalization performance of supervised learning","volume":"2","author":"Xu","year":"2018","journal-title":"J. Anal. Test."},{"key":"mlstabd614bib1530","article-title":"A scaling law for the validation-set training-set size ratio","volume":"1","author":"Guyon","year":"1997","journal-title":"AT&T Bell Laboratories"},{"key":"mlstabd614bib1531","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1080\/00107510500052444","article-title":"Power laws, pareto distributions and Zipf\u2019s law","volume":"46","author":"Newman","year":"2005","journal-title":"Contemp. Phys."},{"key":"mlstabd614bib1532","article-title":"Deployment of machine learning models demystified (part 1) Towards Data Science","author":"Opeyemi","year":"2019"},{"key":"mlstabd614bib1533","article-title":"Deployment of machine learning model demystified (part 2) Medium","author":"Opeyemi","year":"2019"},{"key":"mlstabd614bib1534","first-page":"331","article-title":"Machine learning at facebook: understanding inference at the edge","author":"Wu","year":"2019"},{"key":"mlstabd614bib1535","article-title":"Once for all: train one network and specialize it for efficient deployment","author":"Cai","year":"2019"},{"key":"mlstabd614bib1536","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1007\/s11277-020-07367-2","article-title":"Optimization of metascheduler for cloud machine learning services","volume":"114","author":"Suresh","year":"2020","journal-title":"Wirel. Pers. Commun."},{"key":"mlstabd614bib1537","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.3355203","article-title":"Effective use of the machine learning approaches on different clouds","author":"Kumar","year":"2019"},{"key":"mlstabd614bib1538","first-page":"335","article-title":"Model-driven application refactoring to minimize deployment costs in preemptible cloud resources","author":"Dubois","year":"2016"},{"key":"mlstabd614bib1539","author":""},{"key":"mlstabd614bib1540","article-title":"FlatBuffers documentation","author":"","year":"2020"},{"key":"mlstabd614bib1541","article-title":"What is the state of neural network pruning?","author":"Blalock","year":"2020"},{"key":"mlstabd614bib1542","article-title":"Modeling of pruning techniques for deep neural networks simplification","author":"Pasandi","year":"2020"},{"key":"mlstabd614bib1543","article-title":"Integer quantization for deep learning inference: principles and empirical evaluation","author":"Wu","year":"2020"},{"key":"mlstabd614bib1544","doi-asserted-by":"crossref","DOI":"10.1109\/EMC2-NIPS53020.2019.00020","article-title":"Bit efficient quantization for deep neural networks","author":"Nayak","year":"2019"},{"key":"mlstabd614bib1545","article-title":"Adaptive quantization for deep neural network","author":"Zhou","year":"2017"},{"key":"mlstabd614bib1546","first-page":"7308","article-title":"Quantization networks","author":"Yang","year":"2019"},{"key":"mlstabd614bib1547","article-title":"Effective training of convolutional neural networks with low-bitwidth weights and activations","author":"Zhuang","year":"2019"},{"key":"mlstabd614bib1548","first-page":"5811","article-title":"Training quantized nets: a deeper understanding","author":"Li","year":"2017"},{"key":"mlstabd614bib1549","article-title":"BFloat16: the secret to high performance on cloud TPUs google cloud","author":"Wang","year":"2019"},{"key":"mlstabd614bib1550","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3371154","article-title":"Optimizing deep learning inference on embedded systems through adaptive model selection","volume":"19","author":"Marco","year":"2020","journal-title":"ACM Trans. Embedded Comput. Syst. (TECS)"},{"key":"mlstabd614bib1551","article-title":"How to optimize images for web and performance kinsta blog","author":"Jackson","year":"2020"},{"key":"mlstabd614bib1552","first-page":"181","article-title":"Compression parameters tuning for automatic image optimization in web applications","author":"Leventi\u0107","year":"2016"},{"key":"mlstabd614bib1553","article-title":"Feature visualization distill","author":"Olah","year":"2017"},{"key":"mlstabd614bib1554","article-title":"Explainable deep learning: a field guide for the uninitiated","author":"Xie","year":"2020"},{"key":"mlstabd614bib1555","article-title":"Explainable artificial intelligence: a systematic review","author":"Vilone","year":"2020"},{"key":"mlstabd614bib1556","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","article-title":"Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI","volume":"58","author":"Arrieta","year":"2020","journal-title":"Inf. Fusion"},{"key":"mlstabd614bib1557","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-57321-8_5","article-title":"Explainable reinforcement learning: a survey","author":"Puiutta","year":"2020"},{"key":"mlstabd614bib1558","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1609\/aimag.v40i2.2850","article-title":"DARPA\u2019s explainable artificial intelligence program","volume":"40","author":"Gunning","year":"2019","journal-title":"AI Mag."},{"key":"mlstabd614bib1559","first-page":"5","author":"Samek","year":"2019"},{"key":"mlstabd614bib1560","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.acl-main.491","article-title":"Evaluating explainable AI: which algorithmic explanations help users predict model behavior?","author":"Hase","year":"2020"},{"key":"mlstabd614bib1561","doi-asserted-by":"crossref","first-page":"34605","DOI":"10.1007\/s11042-020-08849-y","article-title":"A brief survey of visual saliency detection","volume":"79","author":"Ullah","year":"2020","journal-title":"Multimedia Tools Appl."},{"key":"mlstabd614bib1562","first-page":"1","author":"Borji","year":"2019"},{"key":"mlstabd614bib1563","doi-asserted-by":"publisher","first-page":"2941","DOI":"10.1109\/TCSVT.2018.2870832","article-title":"Review of visual saliency detection with comprehensive information","volume":"29","author":"Cong","year":"2018","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"mlstabd614bib1564","doi-asserted-by":"publisher","first-page":"5706","DOI":"10.1109\/TIP.2015.2487833","article-title":"Salient object detection: a benchmark","volume":"24","author":"Borji","year":"2015","journal-title":"IEEE Trans. Image Process."},{"key":"mlstabd614bib1565","first-page":"8839","article-title":"There and back again: revisiting backpropagation saliency methods","author":"Rebuffi","year":"2020"},{"key":"mlstabd614bib1566","doi-asserted-by":"publisher","first-page":"1796","DOI":"10.1109\/TMM.2019.2949872","article-title":"Learning reliable visual saliency for model explanations","volume":"22","author":"Wang","year":"2019","journal-title":"IEEE Trans. Multimedia"},{"key":"mlstabd614bib1567","doi-asserted-by":"crossref","DOI":"10.1109\/ICCVW.2019.00510","article-title":"Why are saliency maps noisy? Cause of and solution to noisy saliency maps","author":"Kim","year":"2019"},{"key":"mlstabd614bib1568","first-page":"618","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"key":"mlstabd614bib1569","first-page":"4067","article-title":"Augmented Grad-CAM: heat-maps super resolution through augmentation","author":"Morbidelli","year":"2020"},{"key":"mlstabd614bib1570","article-title":"Smooth grad-CAM++: an enhanced inference level visualization technique for deep convolutional neural network models","author":"Omeiza","year":"2019"},{"key":"mlstabd614bib1571","first-page":"839","article-title":"Grad-Cam++: generalized gradient-based visual explanations for deep convolutional networks","author":"Chattopadhay","year":"2018"},{"key":"mlstabd614bib1572","first-page":"7444","article-title":"U-Cam: visual explanation using uncertainty based class activation maps","author":"Patro","year":"2019"},{"key":"mlstabd614bib1573","article-title":"Saliency prediction in the deep learning era: successes and limitations","author":"Borji","year":"2019"},{"key":"mlstabd614bib1574","article-title":"Revisiting video saliency prediction in the deep learning era","author":"Wang","year":"2019"},{"key":"mlstabd614bib1575","first-page":"2794","article-title":"Adapting grad-CAM for embedding networks","author":"Chen","year":"2020"},{"key":"mlstabd614bib1576","first-page":"983","article-title":"Ablation-CAM: visual explanations for deep convolutional network via gradient-free localization","author":"Ramaswamy","year":"2020"},{"key":"mlstabd614bib1577","first-page":"24","article-title":"Score-CAM: score-weighted visual explanations for convolutional neural networks","author":"Wang","year":"2020"},{"key":"mlstabd614bib1578","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.105326","article-title":"A scalable saliency-based feature selection method with instance-level information","volume":"192","author":"Cancela","year":"2020","journal-title":"Knowl.-Based Syst."},{"key":"mlstabd614bib1579","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1109\/TPAMI.2014.2345401","article-title":"Global contrast based salient region detection","volume":"37","author":"Cheng","year":"2014","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstabd614bib1580","first-page":"55","author":"Nguyen","year":"2019"},{"key":"mlstabd614bib1581","article-title":"Gradient-free activation maximization for identifying effective stimuli","author":"Xiao","year":"2019"},{"key":"mlstabd614bib1582","article-title":"Visualizing higher-layer features of a deep network","volume":"1341","author":"Erhan","year":"2009","journal-title":"University of Montreal"},{"key":"mlstabd614bib1583","article-title":"Inceptionism: going deeper into neural networks google AI blog","author":"Mordvintsev","year":"2015"},{"key":"mlstabd614bib1584","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"mlstabd614bib1585","doi-asserted-by":"publisher","first-page":"e2","DOI":"10.23915\/distill.00002","article-title":"How to use t-SNE effectively","volume":"1","author":"Wattenberg","year":"2016","journal-title":"Distill"},{"key":"mlstabd614bib1586","article-title":"Barnes-Hut-SNE","author":"Van Der Maaten","year":"2013"},{"key":"mlstabd614bib1587","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1038\/324446a0","article-title":"A hierarchical O NlogN force-calculation algorithm","volume":"324","author":"Barnes","year":"1986","journal-title":"Nature"},{"key":"mlstabd614bib1588","article-title":"CNN explainer: learning convolutional neural networks with interactive visualization","author":"Wang","year":"2020"},{"key":"mlstabd614bib1589","first-page":"1","article-title":"CNN 101: interactive visual learning for convolutional neural networks","author":"Wang","year":"2020"},{"key":"mlstabd614bib1590","first-page":"1","article-title":"GAN Lab: understanding complex deep generative models using interactive visual experimentation","volume":"25","author":"Kahng","year":"2018","journal-title":"IEEE Trans. Vis. Comput. Graphics"},{"key":"mlstabd614bib1591","doi-asserted-by":"crossref","first-page":"5019","DOI":"10.1007\/s10462-020-09814-9","article-title":"Applicability of machine learning in spam and phishing email filtering: review and approaches","volume":"53","author":"Gangavarapu","year":"2020","journal-title":"Artif. Intell. Rev."},{"key":"mlstabd614bib1592","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2019.e01802","article-title":"Machine learning for email spam filtering: review, approaches and open research problems","volume":"5","author":"Dada","year":"2019","journal-title":"Heliyon"},{"key":"mlstabd614bib1593","article-title":"A survey of existing e-mail spam filtering methods considering machine learning techniques","volume":"18","author":"Bhuiyan","year":"2018","journal-title":"Glob. J. Comput. Sci. Technol."},{"key":"mlstabd614bib1594","author":"Zhang","year":"2020"},{"key":"mlstabd614bib1595","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1162\/tacl_a_00258","article-title":"Rotational unit of memory: a novel representation unit for rnns with scalable applications","volume":"7","author":"Dangovski","year":"2019","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"mlstabd614bib1596","author":"","year":"2020"},{"key":"mlstabd614bib1597","doi-asserted-by":"publisher","first-page":"37","DOI":"10.5334\/dsj-2019-037","article-title":"Application of natural language processing algorithms to the task of automatic classification of russian scientific texts","volume":"18","author":"Romanov","year":"2019","journal-title":"Data Sci. J."},{"key":"mlstabd614bib1598","doi-asserted-by":"crossref","first-page":"6793","DOI":"10.1007\/s00521-019-04334-2","article-title":"A deep learning classifier for sentence classification in biomedical and computer science abstracts","volume":"32","author":"Gon\u00e7alves","year":"2019","journal-title":"Neural Comput. Appl."},{"key":"mlstabd614bib1599","first-page":"246","article-title":"Medical text classification using convolutional neural networks","volume":"235","author":"Hughes","year":"2017","journal-title":"Stud. Health Technol. Inf."},{"key":"mlstabd614bib1600","article-title":"Automated essay scoring based on two-stage learning","author":"Liu","year":"2019"},{"key":"mlstabd614bib1601","first-page":"153","article-title":"Attention-based recurrent convolutional neural network for automatic essay scoring","author":"Dong","year":"2017"},{"key":"mlstabd614bib1602","first-page":"1882","article-title":"A neural approach to automated essay scoring","author":"Taghipour","year":"2016"},{"key":"mlstabd614bib1603","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P16-1068","article-title":"Automatic text scoring using neural networks","author":"Alikaniotis","year":"2016"},{"key":"mlstabd614bib1604","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3345317","article-title":"Academic plagiarism detection: a systematic literature review","volume":"52","author":"Folt\u00fdnek","year":"2019","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"mlstabd614bib1605","first-page":"120","article-title":"Improving academic plagiarism detection for STEM documents by analyzing mathematical content and citations","author":"Meuschke","year":"2019"},{"key":"mlstabd614bib1606","first-page":"p e5000","author":"Ullah","year":"2018"},{"key":"mlstabd614bib1607","first-page":"1909","article-title":"A machine learning framework to identify students at risk of adverse academic outcomes","author":"Lakkaraju","year":"2015"},{"key":"mlstabd614bib1608","author":"Foster","year":"2019"},{"key":"mlstabd614bib1609","first-page":"717","article-title":"Deep learning in the field of art","author":"Zhan","year":"2019"},{"key":"mlstabd614bib1610","article-title":"Jukebox: a generative model for music","author":"Dhariwal","year":"2020"},{"key":"mlstabd614bib1611","doi-asserted-by":"publisher","first-page":"981","DOI":"10.1007\/s00521-018-3813-6","article-title":"Deep learning for music generation: challenges and directions","volume":"32","author":"Briot","year":"2020","journal-title":"Neural Comput. Appl."},{"key":"mlstabd614bib1612","author":"Briot","year":"2020"},{"key":"mlstabd614bib1613","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"mlstabd614bib1614","article-title":"Better language models and their implications OpenAI blog","author":"Radford","year":"2019"},{"key":"mlstabd614bib1615","first-page":"62","article-title":"Deep learning for source code modeling and generation: models, applications and challenges","volume":"53","author":"Chen","year":"2020","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"mlstabd614bib1616","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3212695","article-title":"A survey of machine learning for big code and naturalness","volume":"51","author":"Allamanis","year":"2018","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"mlstabd614bib1617","author":"","year":"2019"},{"key":"mlstabd614bib1618","doi-asserted-by":"crossref","DOI":"10.1145\/3368089.3417058","article-title":"IntelliCode compose: code generation using transformer","author":"Svyatkovskiy","year":"2020"},{"key":"mlstabd614bib1619","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-64694-3_9","article-title":"DeepClone: modeling clones to generate code predictions","author":"Hammad","year":"2020"},{"key":"mlstabd614bib1620","article-title":"You autocomplete me: poisoning vulnerabilities in neural code completion","author":"Schuster","year":"2020"},{"key":"mlstabd614bib1621","article-title":"Fast and memory-efficient neural code completion","author":"Svyatkovskoy","year":"2020"},{"key":"mlstabd614bib1622","first-page":"960","article-title":"When code completion fails: a case study on real-world completions","author":"Hellendoorn","year":"2019"},{"key":"mlstabd614bib1623","article-title":"DeepCoder: learning to write programs","author":"Balog","year":"2017"},{"key":"mlstabd614bib1624","article-title":"Neural sketch learning for conditional program generation","author":"Murali","year":"2018"},{"key":"mlstabd614bib1625","article-title":"Neural academic paper generation","author":"Demir","year":"2019"},{"key":"mlstabd614bib1626","article-title":"Manuscript writer","author":"","year":"2020"},{"key":"mlstabd614bib1627","article-title":"SCIgen\u2014an automatic CS paper generator","author":"Stribling","year":"2005"},{"key":"mlstabd614bib1628","article-title":"A survey of deep learning for scientific discovery","author":"Raghu","year":"2020"},{"key":"mlstabd614bib1629","article-title":"New phenomena in large-scale internet traffic","author":"Kepner","year":"2019"},{"key":"mlstabd614bib1630","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1186\/s40537-019-0176-5","article-title":"Data mining approach for predicting the daily internet data traffic of a smart university","volume":"6","author":"Adekitan","year":"2019","journal-title":"J. Big Data"},{"key":"mlstabd614bib1631","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1016\/j.chb.2019.04.015","article-title":"Prediction of academic performance associated with internet usage behaviors using machine learning algorithms","volume":"98","author":"Xu","year":"2019","journal-title":"Comput. Human Behav."},{"key":"mlstabd614bib1632","article-title":"Toward the quantification of cognition","author":"Granger","year":"2020"},{"key":"mlstabd614bib1633","doi-asserted-by":"publisher","DOI":"10.2196\/16194","article-title":"An integrated brain-machine interface platform with thousands of channels","volume":"21","author":"Musk","year":"2019","journal-title":"J. Med. Internet Res."},{"key":"mlstabd614bib1634","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1038\/s41586-019-1335-8","article-title":"Unsupervised word embeddings capture latent knowledge from materials science literature","volume":"571","author":"Tshitoyan","year":"2019","journal-title":"Nature"},{"key":"mlstabd614bib1635","doi-asserted-by":"publisher","DOI":"10.21314\/JCF.2020.390","article-title":"Neural networks for option pricing and hedging: a literature review","volume":"24","author":"Ruf","year":"2020","journal-title":"J. Comput. Finance Forthcoming"},{"key":"mlstabd614bib1636","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1080\/17517575.2018.1493145","article-title":"Automated trading systems statistical and machine learning methods and hardware implementation: a survey","volume":"13","author":"Huang","year":"2019","journal-title":"Enterprise Infor. Sys."},{"key":"mlstabd614bib1637","first-page":"469","article-title":"Mitigating bias in algorithmic hiring: evaluating claims and practices","author":"Raghavan","year":"2020"},{"key":"mlstabd614bib1638","first-page":"110","article-title":"Performance predicting in hiring process and performance appraisals using machine learning","author":"Mahmoud","year":"2019"},{"key":"mlstabd614bib1639","first-page":"529","article-title":"Bots, bias and big data: artificial intelligence, algorithmic bias and disparate impact liability in hiring practices","volume":"71","author":"Raub","year":"2018","journal-title":"Ark. Law Rev."},{"key":"mlstabd614bib1640","first-page":"693","article-title":"Reengineering workplace bargaining: how big data drives lower wages and how reframing labor law can restore information equality in the workplace","volume":"85","author":"Newman","year":"2017","journal-title":"Univ. Cincinnati Law Rev."},{"key":"mlstabd614bib1641","first-page":"1","volume":"34","author":"Price","year":"2019","journal-title":"Berkeley Technol. Law J."},{"key":"mlstabd614bib1642","article-title":"The effect of novelty on the future impact of scientific grants","author":"Zhuang","year":"2019"},{"key":"mlstabd614bib1643","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3374217","article-title":"Adversarial attacks on deep-learning models in natural language processing: a survey","volume":"11","author":"Zhang","year":"2020","journal-title":"ACM Trans. Intell. Sys. Technol. (TIST)"},{"key":"mlstabd614bib1644","article-title":"Understanding adversarial attacks on deep learning based medical image analysis systems","volume":"110","author":"Ma","year":"2020","journal-title":"Pattern Recognit."},{"key":"mlstabd614bib1645","doi-asserted-by":"publisher","first-page":"2805","DOI":"10.1109\/TNNLS.2018.2886017","article-title":"Adversarial examples: attacks and defenses for deep learning","volume":"30","author":"Yuan","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Sys."},{"key":"mlstabd614bib1646","doi-asserted-by":"publisher","first-page":"14410","DOI":"10.1109\/ACCESS.2018.2807385","article-title":"Threat of adversarial attacks on deep learning in computer vision: a survey","volume":"6","author":"Akhtar","year":"2018","journal-title":"IEEE Access"},{"key":"mlstabd614bib1647","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014"},{"key":"mlstabd614bib1648","article-title":"Towards understanding the regularization of adversarial robustness on neural networks","author":"Wen","year":"2019"},{"key":"mlstabd614bib1649","first-page":"656","article-title":"Certified robustness to adversarial examples with differential privacy","author":"Lecuyer","year":"2019"},{"key":"mlstabd614bib1650","article-title":"Optimal transport classifier: defending against adversarial attacks by regularized deep embedding","author":"Li","year":"2018"},{"key":"mlstabd614bib1651","first-page":"819","article-title":"Adversarial examples improve image recognition","author":"Xie","year":"2020"},{"key":"mlstabd614bib1652","doi-asserted-by":"crossref","first-page":"935","DOI":"10.1007\/s13042-020-01097-4","article-title":"Robustness to adversarial examples can be improved with overfitting","volume":"11","author":"Deniz","year":"2020","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"mlstabd614bib1653","first-page":"3712","article-title":"Fixed smooth convolutional layer for avoiding checkerboard artifacts in CNNs","author":"Kinoshita","year":"2020"},{"key":"mlstabd614bib1654","article-title":"Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abd614","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abd614\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abd614","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abd614\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abd614\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abd614\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abd614\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abd614\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,19]],"date-time":"2024-08-19T23:25:06Z","timestamp":1724109906000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abd614"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,1]]},"references-count":1654,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,3,31]]},"published-print":{"date-parts":[[2021,3,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/abd614","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,1]]},"assertion":[{"value":"Deep learning in electron microscopy","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2021 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2020-10-05","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2020-12-22","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-03-31","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}