{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T10:15:26Z","timestamp":1778580926129,"version":"3.51.4"},"reference-count":98,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2021,7,19]],"date-time":"2021-07-19T00:00:00Z","timestamp":1626652800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,7,19]],"date-time":"2021-07-19T00:00:00Z","timestamp":1626652800000},"content-version":"tdm","delay-in-days":0,"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":[[2021,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Compressed sensing can decrease scanning transmission electron microscopy electron dose and scan time with minimal information loss. Traditionally, sparse scans used in compressed sensing sample a static set of probing locations. However, dynamic scans that adapt to specimens are expected to be able to match or surpass the performance of static scans as static scans are a subset of possible dynamic scans. Thus, we present a prototype for a contiguous sparse scan system that piecewise adapts scan paths to specimens as they are scanned. Sampling directions for scan segments are chosen by a recurrent neural network (RNN) based on previously observed scan segments. The RNN is trained by reinforcement learning to cooperate with a feedforward convolutional neural network that completes the sparse scans. This paper presents our learning policy, experiments, and example partial scans, and discusses future research directions. Source code, pretrained models, and training data is openly accessible at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/Jeffrey-Ede\/adaptive-scans\" xlink:type=\"simple\">https:\/\/github.com\/Jeffrey-Ede\/adaptive-scans<\/jats:ext-link>.<\/jats:p>","DOI":"10.1088\/2632-2153\/abf5b6","type":"journal-article","created":{"date-parts":[[2021,4,7]],"date-time":"2021-04-07T23:59:41Z","timestamp":1617839981000},"page":"045011","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Adaptive partial scanning transmission electron microscopy with reinforcement learning"],"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":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2021,7,19]]},"reference":[{"key":"mlstabf5b6bib1","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":"mlstabf5b6bib2","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":"mlstabf5b6bib3","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1148\/110.1.109","article-title":"Computerized axial tomography with the EMI scanner","volume":"110","author":"New","year":"1974","journal-title":"Radiology"},{"key":"mlstabf5b6bib4","doi-asserted-by":"publisher","first-page":"185","DOI":"10.7326\/0003-4819-90-2-185","article-title":"Accurate measurement of liver, kidney and spleen volume and mass by computerized axial tomography","volume":"90","author":"Heymsfield","year":"1979","journal-title":"Ann. Intern. Med."},{"key":"mlstabf5b6bib5","volume":"vol 2","author":"Schwartz","year":"2009"},{"key":"mlstabf5b6bib6","first-page":"40","article-title":"Scanning electron microscopy: an introduction","volume":"13","author":"Vernon-Parry","year":"2000","journal-title":"III-Vs Rev."},{"key":"mlstabf5b6bib7","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":"mlstabf5b6bib8","doi-asserted-by":"publisher","DOI":"10.1088\/1674-1056\/27\/6\/066107","article-title":"Scanning transmission electron microscopy: a review of high angle annular dark field and annular bright field imaging and applications in lithium-ion batteries","volume":"27","author":"Tong","year":"2018","journal-title":"Chin. Phys. B"},{"key":"mlstabf5b6bib9","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":"mlstabf5b6bib10","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":"mlstabf5b6bib11","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":"mlstabf5b6bib12","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":"mlstabf5b6bib13","doi-asserted-by":"publisher","DOI":"10.1098\/rsos.140550","volume":"2","author":"Sub-Nyquist Artefacts","year":"2015","journal-title":"R. Soc. Open Sci."},{"key":"mlstabf5b6bib14","first-page":"pp 73","author":"Binev","year":"2012"},{"key":"mlstabf5b6bib15","article-title":"Review: deep learning in electron microscopy","author":"Ede","year":"2020"},{"key":"mlstabf5b6bib16","doi-asserted-by":"publisher","first-page":"8332","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":"mlstabf5b6bib17","article-title":"Deep reinforcement learning: an overview","author":"Li","year":"2017"},{"key":"mlstabf5b6bib18","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":"mlstabf5b6bib19","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":"mlstabf5b6bib20","doi-asserted-by":"publisher","author":"Anderson","year":"2013","DOI":"10.1117\/12.2008313"},{"key":"mlstabf5b6bib21","doi-asserted-by":"crossref","DOI":"10.1101\/740548","article-title":"Deep learning-based point-scanning super-resolution imaging","author":"Fang","year":"2019"},{"key":"mlstabf5b6bib22","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":"mlstabf5b6bib23","article-title":"Deep learning supersampled scanning transmission electron microscopy","author":"Ede","year":"2019"},{"key":"mlstabf5b6bib24","article-title":"Selection of optimal views for computed tomography reconstruction","author":"Mueller","year":"2011"},{"key":"mlstabf5b6bib25","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1109\/TIP.2009.2032889","article-title":"Variable density compressed image sampling","volume":"19","author":"Wang","year":"2009","journal-title":"IEEE Trans. Image Process."},{"key":"mlstabf5b6bib26","doi-asserted-by":"publisher","first-page":"2346","DOI":"10.1109\/TSP.2007.914345","article-title":"Bayesian compressive sensing","volume":"56","author":"Ji","year":"2008","journal-title":"IEEE Trans. Signal Process."},{"key":"mlstabf5b6bib27","first-page":"pp 912","author":"Seeger","year":"2008"},{"key":"mlstabf5b6bib28","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1109\/JSTSP.2015.2400428","article-title":"Info-greedy sequential adaptive compressed sensing","volume":"9","author":"Braun","year":"2015","journal-title":"IEEE J. Sel. Top. Sig. Process."},{"key":"mlstabf5b6bib29","doi-asserted-by":"publisher","first-page":"1185","DOI":"10.1137\/120878380","article-title":"Design with application to compressive sensing","volume":"5","author":"Carson","year":"2012","journal-title":"SIAM J. Imaging Sci."},{"key":"mlstabf5b6bib30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TCI.2017.2777482","article-title":"A framework for dynamic image sampling based on supervised learning","volume":"4","author":"Godaliyadda","year":"2017","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"mlstabf5b6bib31","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/s11760-017-1177-5","article-title":"Sparse fast Fourier transform for exactly sparse signals and signals with additive Gaussian noise","volume":"12","author":"Ermeydan","year":"2018","journal-title":"Sig. Image Video Process."},{"key":"mlstabf5b6bib32","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":"mlstabf5b6bib33","first-page":"pp 345","article-title":"Reinforcement learning algorithm for partially observable Markov decision problems","author":"Jaakkola","year":"1995"},{"key":"mlstabf5b6bib34","doi-asserted-by":"publisher","first-page":"6","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":"mlstabf5b6bib35","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":"mlstabf5b6bib36","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":"mlstabf5b6bib37","author":"Olah","year":"2015"},{"key":"mlstabf5b6bib38","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/D14-1179","article-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","author":"Cho","year":"2014"},{"key":"mlstabf5b6bib39","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":"mlstabf5b6bib40","first-page":"pp 2342","article-title":"An empirical exploration of recurrent network architectures","author":"Jozefowicz","year":"2015"},{"key":"mlstabf5b6bib41","first-page":"pp 755","article-title":"Evolving memory cell structures for sequence learning","author":"Bayer","year":"2009"},{"key":"mlstabf5b6bib42","first-page":"pp 1310","article-title":"On the difficulty of training recurrent neural networks","author":"Pascanu","year":"2013"},{"key":"mlstabf5b6bib43","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":"mlstabf5b6bib44","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":"mlstabf5b6bib45","article-title":"Overview of gradient descent optimization algorithms","author":"An","year":"2016"},{"key":"mlstabf5b6bib46","first-page":"pp 2204","article-title":"Recurrent models of visual attention","author":"Mnih","year":"2014"},{"key":"mlstabf5b6bib47","article-title":"Multiple object recognition with visual attention","author":"Ba","year":"2014"},{"key":"mlstabf5b6bib48","author":"Vinyals","year":"2019"},{"key":"mlstabf5b6bib49","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015"},{"key":"mlstabf5b6bib50","article-title":"Memory-based control with recurrent neural networks","author":"Heess","year":"2015"},{"key":"mlstabf5b6bib51","article-title":"Learning surrogate losses","author":"Grabocka","year":"2019"},{"key":"mlstabf5b6bib52","first-page":"pp 1008","author":"Konda","year":"2000"},{"key":"mlstabf5b6bib53","first-page":"pp 262","article-title":"Analysis and improvement of policy gradient estimation","author":"Zhao","year":"2011"},{"key":"mlstabf5b6bib54","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":"mlstabf5b6bib55","article-title":"Optimizing deep learning hyper-parameters through an evolutionary algorithm","volume":"pp 1\u20135","author":"Young","year":"2015"},{"key":"mlstabf5b6bib56","article-title":"Deep neuroevolution: genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning","author":"Such","year":"2017"},{"key":"mlstabf5b6bib57","first-page":"pp 265","article-title":"Tensorflow: a system for large-scale machine learning","author":"Abadi","year":"2016"},{"key":"mlstabf5b6bib58","author":"Ede","year":"2020"},{"key":"mlstabf5b6bib59","author":"Ede","year":"2020"},{"key":"mlstabf5b6bib60","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":"mlstabf5b6bib61","article-title":"Parameter space noise for exploration","author":"Plappert","year":"2017"},{"key":"mlstabf5b6bib62","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"},{"key":"mlstabf5b6bib63","article-title":"Distributed distributional deterministic policy gradients","author":"Barth-Maron","year":"2018"},{"key":"mlstabf5b6bib64","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":"mlstabf5b6bib65","article-title":"Model evaluation, model selection, and algorithm selection in machine learning","author":"Raschka","year":"2018"},{"key":"mlstabf5b6bib66","doi-asserted-by":"publisher","first-page":"1328","DOI":"10.1109\/TKDE.2019.2946162","article-title":"Survey on data collection for machine learning: a big data-AI integration perspective","volume":"33","author":"Roh","year":"2019","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"mlstabf5b6bib67","article-title":"Recurrent neural network regularization","author":"Zaremba","year":"2014"},{"key":"mlstabf5b6bib68","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":"mlstabf5b6bib69","first-page":"pp 1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012"},{"key":"mlstabf5b6bib70","article-title":"Look at experience replay","author":"Zhang","year":"2017"},{"key":"mlstabf5b6bib71","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":"mlstabf5b6bib72","article-title":"ADAM: a method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"mlstabf5b6bib73","first-page":"pp 464","article-title":"Cyclical learning rates for training neural networks","author":"Smith","year":"2017"},{"key":"mlstabf5b6bib74","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-decoder","volume":"202","author":"Ede","year":"2019","journal-title":"Ultramicroscopy"},{"key":"mlstabf5b6bib75","first-page":"pp 4287","article-title":"Learning values across many orders of magnitude","author":"van Hasselt","year":"2016"},{"key":"mlstabf5b6bib76","article-title":"Distilling policy distillation","author":"Czarnecki","year":"2019"},{"key":"mlstabf5b6bib77","article-title":"Combating reinforcement learning\u2019s Sisyphean curse with intrinsic fear","author":"Lipton","year":"2016"},{"key":"mlstabf5b6bib78","first-page":"pp 2573","article-title":"Reinterpretation of the policy oscillation phenomenon in approximate policy iteration","author":"Wagner","year":"2011"},{"key":"mlstabf5b6bib79","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/2061827","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":"mlstabf5b6bib80","first-page":"pp 278","article-title":"Policy invariance under reward transformations: theory and application to reward shaping","volume":"vol 99","author":"Ng","year":"1999"},{"key":"mlstabf5b6bib81","article-title":"AdaNet: a scalable and flexible framework for automatically learning ensembles","author":"Weill","year":"2019"},{"key":"mlstabf5b6bib82","article-title":"Ludwig: a type-based declarative deep learning toolbox","author":"Molino","year":"2019"},{"key":"mlstabf5b6bib83","article-title":"a survey of the state-of-the-art","author":"He","year":"2019"},{"key":"mlstabf5b6bib84","article-title":"Modeling neural architecture search methods for deep networks","author":"Malekhosseini","year":"2019"},{"key":"mlstabf5b6bib85","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":"mlstabf5b6bib86","article-title":"Neural architecture search: a survey","author":"Elsken","year":"2018"},{"key":"mlstabf5b6bib87","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":"mlstabf5b6bib88","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":"mlstabf5b6bib89","first-page":"pp 8697","article-title":"Learning transferable architectures for scalable image recognition","author":"Zoph","year":"2018"},{"key":"mlstabf5b6bib90","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":"mlstabf5b6bib91","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":"mlstabf5b6bib92","first-page":"pp 2223","article-title":"Unpaired image-to-image translation using cycle-consistent adversarial networks","author":"Zhu","year":"2017"},{"key":"mlstabf5b6bib93","author":"Ede","year":"2020"},{"key":"mlstabf5b6bib94","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":"mlstabf5b6bib95","first-page":"pp 6968","article-title":"High-quality self-supervised deep image denoising","author":"Laine","year":"2019"},{"key":"mlstabf5b6bib96","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1017\/S1431927619001909","article-title":"Real-time data processing using python in digital micrograph","volume":"25","author":"Miller","year":"2019","journal-title":"Microsc. Microanal."},{"key":"mlstabf5b6bib97","first-page":"pp 1","article-title":"LeFlow: enabling flexible FPGA high-level synthesis of tensorflow deep neural networks","author":"Noronha","year":"2018"},{"key":"mlstabf5b6bib98","doi-asserted-by":"crossref","first-page":"2124","DOI":"10.1109\/TCSII.2019.2943958","article-title":"Reinforcement learning based Markov-decision process (MDP) implementation for SRAM FPGAs","volume":"67","author":"Ruan","year":"2019","journal-title":"IEEE Trans. Circuits Syst. II: Express Briefs"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf5b6","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf5b6\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf5b6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf5b6\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf5b6\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf5b6\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf5b6\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf5b6\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,12]],"date-time":"2021-12-12T17:53:09Z","timestamp":1639331589000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf5b6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,19]]},"references-count":98,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2021,7,19]]},"published-print":{"date-parts":[[2021,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/abf5b6","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,19]]},"assertion":[{"value":"Adaptive partial scanning transmission electron microscopy with reinforcement learning","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":"2020-12-22","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-04-07","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-07-19","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}