{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T11:38:54Z","timestamp":1765280334901,"version":"3.37.3"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2022,7,8]],"date-time":"2022-07-08T00:00:00Z","timestamp":1657238400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,7,8]],"date-time":"2022-07-08T00:00:00Z","timestamp":1657238400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100014188","name":"ministry of science and ict","doi-asserted-by":"crossref","award":["2016M3A7B4910348"],"award-info":[{"award-number":["2016M3A7B4910348"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100014188","name":"ministry of science and ict","doi-asserted-by":"crossref","award":["2021M3F3A2A01037927"],"award-info":[{"award-number":["2021M3F3A2A01037927"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2023,3]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>This work focuses on the optimization of the structural complexity of a single-layer feedforward neural network (SLFN) for neuromorphic hardware implementation. The singular value decomposition (SVD) method is used for the determination of the effective number of neurons in the hidden layer for Modified National Institute of Standards and Technology (MNIST) dataset classification. The proposed method is also verified on a SLFN using weights derived from a synaptic transistor device. The effectiveness of this methodology in estimating the reduced number of neurons in the hidden layer makes this method highly useful in optimizing complex neural network architectures for their hardware realization.<\/jats:p>","DOI":"10.1007\/s10489-022-03783-y","type":"journal-article","created":{"date-parts":[[2022,7,8]],"date-time":"2022-07-08T04:02:39Z","timestamp":1657252959000},"page":"6288-6306","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Optimization of the structural complexity of artificial neural network for hardware-driven neuromorphic computing application"],"prefix":"10.1007","volume":"53","author":[{"given":"Kannan","family":"Udaya Mohanan","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8520-718X","authenticated-orcid":false,"given":"Seongjae","family":"Cho","sequence":"additional","affiliation":[]},{"given":"Byung-Gook","family":"Park","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,7,8]]},"reference":[{"key":"3783_CR1","doi-asserted-by":"publisher","first-page":"130678","DOI":"10.1109\/ACCESS.2020.3005303","volume":"8","author":"JH Ryu","year":"2020","unstructured":"Ryu JH, Kim B, Hussain F, Ismail M, Mahata C, Oh T, Imran M, Min KK, Kim TH, Yang BD, Cho S, Park BG, Kim Y, Kim S (2020) Zinc tin oxide synaptic device for neuromorphic engineering. IEEE Access 8:130678\u2013130686. https:\/\/doi.org\/10.1109\/ACCESS.2020.3005303","journal-title":"IEEE Access"},{"issue":"1","key":"3783_CR2","doi-asserted-by":"publisher","first-page":"30","DOI":"10.5573\/JSTS.2022.22.1.30","volume":"22","author":"S Cho","year":"2022","unstructured":"Cho S (2022) Volatile and nonvolatile memory devices for neuromorphic and processing-in-memory applications. J Semicond Technol Sci 22(1):30\u201346. https:\/\/doi.org\/10.5573\/JSTS.2022.22.1.30","journal-title":"J Semicond Technol Sci"},{"key":"3783_CR3","doi-asserted-by":"publisher","first-page":"123","DOI":"10.3389\/fnins.2017.00123","volume":"11","author":"I Sourikopoulos","year":"2017","unstructured":"Sourikopoulos I, Hedayat S, Loyez C, Danneville F, Hoel V, Mercier E, Cappy A (2017) A 4-fJ\/Spike artificial neuron in 65 nm CMOS technology. Front Neurosci 11:123. https:\/\/doi.org\/10.3389\/fnins.2017.00123","journal-title":"Front Neurosci"},{"issue":"1","key":"3783_CR4","doi-asserted-by":"publisher","first-page":"2331","DOI":"10.1038\/s41467-018-04482-4","volume":"9","author":"FM Bayat","year":"2018","unstructured":"Bayat FM, Prezioso M, Chakrabarti B, Nili H, Kataeva I, Strukov D (2018) Implementation of multilayer perceptron network with highly uniform passive memristive crossbar circuits. Nat Commun 9(1):2331. https:\/\/doi.org\/10.1038\/s41467-018-04482-4","journal-title":"Nat Commun"},{"key":"3783_CR5","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.sse.2017.10.012","volume":"140","author":"JJ Lee","year":"2018","unstructured":"Lee JJ, Park J, Kwon MW, Hwang S, Kim H, Park BG (2018) Integrated neuron circuit for implementing neuromorphic system with synaptic device. Solid State Electron 140:34\u201340. https:\/\/doi.org\/10.1016\/j.sse.2017.10.012","journal-title":"Solid State Electron"},{"issue":"5","key":"3783_CR6","doi-asserted-by":"publisher","first-page":"050905","DOI":"10.35848\/1347-4065\/abf4a0","volume":"60","author":"MH Kim","year":"2021","unstructured":"Kim MH, Cho S, Park BG (2021) Nanoscale wedge resistive-switching synaptic device and experimental verification of vector-matrix multiplication for hardware neuromorphic application. Jpn J Appl Phys 60(5):050905. https:\/\/doi.org\/10.35848\/1347-4065\/abf4a0","journal-title":"Jpn J Appl Phys"},{"key":"3783_CR7","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Deep learning (MIT Press)"},{"issue":"6197","key":"3783_CR8","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1126\/science.1254642","volume":"345","author":"PA Merolla","year":"2014","unstructured":"Merolla PA, Arthur JV, Alvarez-Icaza R, Cassidy AS, Sawada J, Akopyan F, Jackson BL, Imam N, Guo C, Nakamura Y, Brezzo B, Vo I, Esser SK, Appuswamy R, Taba B, Amir A, Flickner MD, Risk WP, Manohar R, Modha DS (2014) A million spiking-neuron integrated circuit with a scalable communication network and interface. Science 345(6197):668\u2013673. https:\/\/doi.org\/10.1126\/science.1254642","journal-title":"Science"},{"issue":"5","key":"3783_CR9","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1109\/JPROC.2014.2313565","volume":"102","author":"BV Benjamin","year":"2014","unstructured":"Benjamin BV, Gao P, McQuinn E, Choudhary S, Chandrasekaran AR, Bussat JM, Alvarez-Icaza R, Arthur JV, Merolla PA, Boahen K (2014) Neurogrid: a mixed-analog-digital multichip system for large-scale neural simulations. Proc IEEE 102(5):699\u2013716. https:\/\/doi.org\/10.1109\/JPROC.2014.2313565","journal-title":"Proc IEEE"},{"issue":"1","key":"3783_CR10","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1109\/JPROC.2018.2881432","volume":"107","author":"A Neckar","year":"2019","unstructured":"Neckar A, Fok S, Benjamin BV, Stewart TC, Oza NN, Voelker AR, Eliasmith C, Manohar R, Boahen K (2019) Braindrop: a mixed-signal neuromorphic architecture with a dynamical systems-based programming model. Proc IEEE 107(1):144\u2013164. https:\/\/doi.org\/10.1109\/JPROC.2018.2881432","journal-title":"Proc IEEE"},{"key":"3783_CR11","doi-asserted-by":"crossref","unstructured":"Schemmel J, Br\u00fcderle D, Gr\u00fcbl A., Hock M, Meier K, Millner S (2010) A wafer-scale neuromorphic hardware system for large-scale neural modeling. In: Proceedings of 2010 IEEE international symposium on circuits and systems, pp 1947\u20131950","DOI":"10.1109\/ISCAS.2010.5536970"},{"key":"3783_CR12","doi-asserted-by":"publisher","unstructured":"Brown A, Furber S (2009) Biologically-inspired massively-parallel architectures - computing beyond a million processors. In: 2010 10th International conference on application of concurrency to system design ieee computer society, Los Alamitos, CA, USA, pp 3\u201312. https:\/\/doi.org\/10.1109\/ACSD.2009.17","DOI":"10.1109\/ACSD.2009.17"},{"key":"3783_CR13","doi-asserted-by":"publisher","first-page":"141","DOI":"10.3389\/fnins.2015.00141","volume":"9","author":"N Qiao","year":"2015","unstructured":"Qiao N, Mostafa H, Corradi F, Osswald M, Stefanini F, Sumislawska D, Indiveri G (2015) A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128K synapses. Front Neurosci 9:141. 10.3389\/fnins.2015.00141","journal-title":"Front Neurosci"},{"key":"3783_CR14","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.sysarc.2017.01.003","volume":"77","author":"D Ma","year":"2017","unstructured":"Ma D, Shen J, Gu Z, Zhang M, Zhu X, Xu X, Xu Q, Shen Y, Pan G (2017) Darwin: a neuromorphic hardware co-processor based on spiking neural networks. J Syst Archit 77:43\u201351. https:\/\/doi.org\/10.1016\/j.sysarc.2017.01.003","journal-title":"J Syst Archit"},{"key":"3783_CR15","doi-asserted-by":"publisher","first-page":"891","DOI":"10.3389\/fnins.2018.00891","volume":"12","author":"CS Thakur","year":"2018","unstructured":"Thakur CS, Molin JL, Cauwenberghs G, Indiveri G, Kumar K, Qiao N, Schemmel J, Wang R, Chicca E, Olson Hasler J, Seo JS, Yu S, Cao Y, Schaik AV, Etienne-Cummings R (2018) Large-scale neuromorphic spiking array processors: a quest to mimic the brain. Front Neurosci 12:891. https:\/\/doi.org\/10.3389\/fnins.2018.00891","journal-title":"Front Neurosci"},{"issue":"8","key":"3783_CR16","doi-asserted-by":"publisher","first-page":"3801","DOI":"10.1109\/TED.2021.3089450","volume":"68","author":"YT Seo","year":"2021","unstructured":"Seo YT, Kwon D, Noh Y, Lee S, Park MK, Woo SY, Park BG, Lee JH (2021) 3-D And-type flash memory architecture with high-\u00ee gate dielectric for high-density synaptic devices. IEEE Trans Electron Devices 68(8):3801\u20133806. https:\/\/doi.org\/10.1109\/TED.2021.3089450","journal-title":"IEEE Trans Electron Devices"},{"key":"3783_CR17","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.sse.2018.10.003","volume":"150","author":"S Bang","year":"2018","unstructured":"Bang S, Kim MH, Kim TH, Lee DK, Kim S, Cho S, Park BG (2018) Gradual switching and self-rectifying characteristics of Cu\/\u03b1-IGZO\/p+-Si RRAM for synaptic device application. Solid State Electron 150:60\u201365. https:\/\/doi.org\/10.1016\/j.sse.2018.10.003","journal-title":"Solid State Electron"},{"key":"3783_CR18","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1016\/j.mee.2018.01.009","volume":"190","author":"D Ielmini","year":"2018","unstructured":"Ielmini D (2018) Brain-inspired computing with resistive switching memory (RRAM): Devices, synapses and neural networks. Microelectron Eng 190:44\u201353. https:\/\/doi.org\/10.1016\/j.mee.2018.01.009","journal-title":"Microelectron Eng"},{"key":"3783_CR19","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.sse.2019.02.008","volume":"154","author":"DK Lee","year":"2019","unstructured":"Lee DK, Kim MH, Kim TH, Bang S, Choi YJ, Kim S, Cho S, Park BG (2019) Synaptic behaviors of HfO2 ReRAM by pulse frequency modulation. Solid State Electron 154:31\u201335. https:\/\/doi.org\/10.1016\/j.sse.2019.02.008","journal-title":"Solid State Electron"},{"key":"3783_CR20","doi-asserted-by":"publisher","first-page":"160204","DOI":"10.1016\/j.jallcom.2021.160204","volume":"877","author":"U Rasheed","year":"2021","unstructured":"Rasheed U, Ryu H, Mahata C, Khalil RMA, Imran M, Rana AM, Kousar F, Kim B, Kim Y, Cho S, Hussain F, Kim S (2021) Resistive switching characteristics and theoretical simulation of a Pt\/a-Ta2O5\/TiN synaptic device for neuromorphic applications. J Alloys Compd 877:160204. https:\/\/doi.org\/10.1016\/j.jallcom.2021.160204","journal-title":"J Alloys Compd"},{"key":"3783_CR21","doi-asserted-by":"publisher","unstructured":"Ambrogio S, Ciocchini N, Laudato M, Milo V, Pirovano A, Fantini P, Ielmini D (2016) Unsupervised learning by spike timing dependent plasticity in phase change memory (PCM) synapses. Front Neurosci, vol 10, (56), https:\/\/doi.org\/10.3389\/fnins.2016.00056","DOI":"10.3389\/fnins.2016.00056"},{"issue":"4","key":"3783_CR22","doi-asserted-by":"publisher","first-page":"2001276","DOI":"10.1002\/aelm.202001276","volume":"7","author":"M Yan","year":"2021","unstructured":"Yan M, Zhu Q, Wang S, Ren Y, Feng G, Liu L, Peng H, He Y, Wang J, Zhou P, Meng X, Tang X, Chu J, Dkhil B, Tian B, Duan C (2021) Ferroelectric synaptic transistor network for associative memory. Adv Electron Mater 7(4):2001276. https:\/\/doi.org\/10.1002\/aelm.202001276","journal-title":"Adv Electron Mater"},{"issue":"7","key":"3783_CR23","doi-asserted-by":"publisher","first-page":"1126","DOI":"10.1109\/LED.2020.2995819","volume":"41","author":"Y Shi","year":"2020","unstructured":"Shi Y, Oh S, Huang Z, Lu X, Kang SH, Kuzum D (2020) Performance prospects of deeply scaled spin-transfer torque magnetic random-access memory for in-memory computing. IEEE Electron Device Lett 41(7):1126\u20131129. https:\/\/doi.org\/10.1109\/LED.2020.2995819","journal-title":"IEEE Electron Device Lett"},{"issue":"9","key":"3783_CR24","doi-asserted-by":"publisher","first-page":"6400","DOI":"10.1007\/s10489-021-02293-7","volume":"51","author":"SK Pal","year":"2021","unstructured":"Pal SK, Pramanik A, Maiti J, Mitra P (2021) Deep learning in multi-object detection and tracking: state of the art. Appl Intell 51(9):6400\u20136429. https:\/\/doi.org\/10.1007\/s10489-021-02293-7","journal-title":"Appl Intell"},{"key":"3783_CR25","doi-asserted-by":"publisher","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1\u20139. https:\/\/doi.org\/10.1109\/CVPR.2015.7298594","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"3783_CR26","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition"},{"key":"3783_CR27","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition","DOI":"10.1109\/CVPR.2016.90"},{"issue":"7","key":"3783_CR28","doi-asserted-by":"publisher","first-page":"1773","DOI":"10.3390\/nano11071773","volume":"11","author":"MHR Ansari","year":"2021","unstructured":"Ansari MHR, Kannan UM, Cho S (2021) Core-shell dual-gate nanowire charge-trap memory for synaptic operations for neuromorphic applications. Nanomaterials 11(7):1773","journal-title":"Nanomaterials"},{"issue":"6","key":"3783_CR29","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1016\/S0893-6080(05)80130-3","volume":"6","author":"M Arai","year":"1993","unstructured":"Arai M (1993) Bounds on the number of hidden units in binary-valued three-layer neural networks. Neural Netw 6(6):855. https:\/\/doi.org\/10.1016\/S0893-6080(05)80130-3","journal-title":"Neural Netw"},{"issue":"2","key":"3783_CR30","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1109\/72.557662","volume":"8","author":"S Tamura","year":"1997","unstructured":"Tamura S, Tateishi M (1997) Capabilities of a four-layered feedforward neural network: four layers versus three. IEEE Trans Neural Netw 8(2):251. https:\/\/doi.org\/10.1109\/72.557662","journal-title":"IEEE Trans Neural Netw"},{"issue":"5","key":"3783_CR31","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1016\/S0893-6080(98)00043-4","volume":"11","author":"O Fujita","year":"1998","unstructured":"Fujita O (1998) Statistical estimation of the number of hidden units for feedforward neural networks. Neural Netw 11(5):851. https:\/\/doi.org\/10.1016\/S0893-6080(98)00043-4","journal-title":"Neural Netw"},{"issue":"6","key":"3783_CR32","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TNN.2006.880582","volume":"17","author":"EJ Teoh","year":"2006","unstructured":"Teoh EJ, Tan KC, Xiang C (2006) Estimating the number of hidden neurons in a feedforward network using the singular value decomposition. IEEE Trans Neural Netw 17(6):1623\u20131629. https:\/\/doi.org\/10.1109\/TNN.2006.880582","journal-title":"IEEE Trans Neural Netw"},{"key":"3783_CR33","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.ins.2020.11.009","volume":"552","author":"FEJ Fernandes","year":"2021","unstructured":"Fernandes FEJ, Yen GG (2021) Pruning deep convolutional neural networks architectures with evolution strategy. Inf Sci 552:29\u201347. https:\/\/doi.org\/10.1016\/j.ins.2020.11.009","journal-title":"Inf Sci"},{"key":"3783_CR34","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1016\/j.neunet.2019.11.018","volume":"123","author":"L Wen","year":"2020","unstructured":"Wen L, Zhang X, Bai H, Xu Z (2020) Structured pruning of recurrent neural networks through neuron selection. Neural Netw 123:134\u2013141","journal-title":"Neural Netw"},{"key":"3783_CR35","doi-asserted-by":"publisher","first-page":"107899","DOI":"10.1016\/j.patcog.2021.107899","volume":"115","author":"SK Yeom","year":"2021","unstructured":"Yeom SK, Seegerer P, Lapuschkin S, Binder A, Wiedemann S, M\u00fcller K. R., Samek W (2021) Pruning by explaining: a novel criterion for deep neural network pruning. Pattern Recogn 115:107899. https:\/\/doi.org\/10.1016\/j.patcog.2021.107899","journal-title":"Pattern Recogn"},{"key":"3783_CR36","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.neucom.2019.08.003","volume":"367","author":"N Floropoulos","year":"2019","unstructured":"Floropoulos N, Tefas A (2019) Complete vector quantization of feedforward neural networks. Neurocomputing 367:55\u201363","journal-title":"Neurocomputing"},{"key":"3783_CR37","doi-asserted-by":"publisher","unstructured":"Pal C, Pankaj S, Akram W, Acharyya A, Biswas D (2018) Modified Huffman based compression methodology for deep neural network implementation on resource constrained mobile platforms. IEEE Int Symp Circuits Syst (ISCAS), pp 1\u20135, https:\/\/doi.org\/10.1109\/ISCAS.2018.8351234","DOI":"10.1109\/ISCAS.2018.8351234"},{"key":"3783_CR38","unstructured":"Mellor J, Turner J, Storkey A, Crowley EJ (2021) Neural architecture search without training. In: Meila M, Zhang T (eds) Proceedings of the 38th international conference on machine learning, proceedings of machine learning research, vol 39, pp 7588\u20137598"},{"key":"3783_CR39","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/JEDS.2020.3011409","volume":"8","author":"E Yu","year":"2020","unstructured":"Yu E, Cho S, Roy K, Park BG (2020) A quantum-well charge-trap synaptic transistor with highly linear weight tunability. IEEE J Electron Devices Soc 8:834\u2013840. https:\/\/doi.org\/10.1109\/JEDS.2020.3011409","journal-title":"IEEE J Electron Devices Soc"},{"issue":"15","key":"3783_CR40","doi-asserted-by":"publisher","first-page":"152107","DOI":"10.1063\/1.5031929","volume":"124","author":"MW Kwon","year":"2018","unstructured":"Kwon MW, Baek MH, Hwang S, Park K, Jang T, Kim T, Lee J, Cho S, Park BG (2018) Integrate-and-fire neuron circuit using positive feedback field effect transistor for low power operation. J Appl Phys 124(15):152107. https:\/\/doi.org\/10.1063\/1.5031929","journal-title":"J Appl Phys"},{"key":"3783_CR41","doi-asserted-by":"publisher","unstructured":"Bartolozzi C, Benosman R, Boahen K, Cauwenberghs G, Delbr\u00fcck T, Indiveri G, Liu SC, Furber S, Imam N, Linares-Barranco B, Serrano-Gotarredona T, Meier K, Posch C, Valle M (2016) Neuromorphic systems, Wiley encyclopedia of electrical and electronics engineering. Wiley, pp 1\u201322, https:\/\/doi.org\/10.1002\/047134608X.W8328","DOI":"10.1002\/047134608X.W8328"},{"key":"3783_CR42","doi-asserted-by":"publisher","unstructured":"Blum A, Hopcroft J, Kannan R (2020) Foundations of data science (Cambridge University Press), https:\/\/doi.org\/10.1017\/9781108755528","DOI":"10.1017\/9781108755528"},{"issue":"4","key":"3783_CR43","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1137\/1015095","volume":"15","author":"GW Stewart","year":"1973","unstructured":"Stewart GW (1973) Error and perturbation bounds for subspaces associated with certain eigenvalue problems. SIAM Rev 15(4):727","journal-title":"SIAM Rev"},{"issue":"6","key":"3783_CR44","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TNN.2006.880582","volume":"17","author":"EJ Teoh","year":"2006","unstructured":"Teoh EJ, Tan KC, Xiang C (2006) Estimating the number of hidden neurons in a feedforward network using the singular value decomposition. IEEE Trans Neural Netw 17(6):1623. https:\/\/doi.org\/10.1109\/TNN.2006.880582","journal-title":"IEEE Trans Neural Netw"},{"issue":"10","key":"3783_CR45","doi-asserted-by":"publisher","first-page":"2011","DOI":"10.1162\/NECO_a_00882","volume":"28","author":"D Marti","year":"2016","unstructured":"Marti D, Rigotti M, Seok M, Fusi S (2016) Energy-efficient neuromorphic classifiers. Neural Comput 28(10):2011\u20132044","journal-title":"Neural Comput"},{"issue":"11","key":"3783_CR46","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324. https:\/\/doi.org\/10.1109\/5.726791","journal-title":"Proc IEEE"},{"key":"3783_CR47","unstructured":"Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L, Desmaison A, Kopf A, Yang E, DeVito Z, Raison M, Tejani A, Chilamkurthy S, Steiner B, Fang L, Bai J, Chintala S (2019) PyTorch: an imperative style, high-performance deep learning library. In: Wallach H, Larochelle H, Beygelzimer A, D\u2019Alch\u00e9-Buc F, Fox E, Garnett R (eds) Advances in neural information processing systems 32, pp 8024\u20138035,(Curran Associates, Inc.)"},{"key":"3783_CR48","unstructured":"Xiao H, Rasul K, Vollgraf R (2017) Fashion-MNIST: a novel image dataset for benchmarking machine learning"},{"key":"3783_CR49","unstructured":"Netzer Y, Wang T, Coates A, Bissacco A, Wu B, Ng AY (2011) Reading digits in natural images with unsupervised feature learning. In: NIPS workshop on deep learning and unsupervised feature learning 2011"},{"key":"3783_CR50","unstructured":"Cohen N, Sharir O, Shashua A (2016) On the Expressive Power of Deep Learning: A Tensor Analysis. In: Feldman V, Rakhlin A, Shamir O (eds) 29th Annual conference on learning theory, proceedings of machine learning research, vol 49, pp 698\u2013728, PMLR, Columbia University, New York"},{"key":"3783_CR51","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.neunet.2017.07.002","volume":"94","author":"D Yarotsky","year":"2017","unstructured":"Yarotsky D (2017) Error bounds for approximations with deep ReLU networks. Neural Netw 94:103. https:\/\/doi.org\/10.1016\/j.neunet.2017.07.002","journal-title":"Neural Netw"},{"issue":"1","key":"3783_CR52","doi-asserted-by":"publisher","first-page":"2143","DOI":"10.1038\/s41467-021-22332-8","volume":"12","author":"S Subbulakshmi Radhakrishnan","year":"2021","unstructured":"Subbulakshmi Radhakrishnan S, Sebastian A, Oberoi A, Das S, Das S (2021) A biomimetic neural encoder for spiking neural network. Nat Commun 12(1):2143. https:\/\/doi.org\/10.1038\/s41467-021-22332-8","journal-title":"Nat Commun"},{"key":"3783_CR53","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1016\/j.neunet.2020.04.025","volume":"128","author":"Z Yan","year":"2020","unstructured":"Yan Z, Chen J, Hu R, Huang T, Chen Y, Wen S (2020) Training memristor-based multilayer neuromorphic networks with SGD, momentum and adaptive learning rates. Neural Netw 128:142\u2013149","journal-title":"Neural Netw"},{"key":"3783_CR54","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.neunet.2016.10.012","volume":"86","author":"MF Mohammed","year":"2017","unstructured":"Mohammed MF, Lim CP (2017) A new hyperbox selection rule and a pruning strategy for the enhanced fuzzy min\u00e2max neural network. Neural Netw 86:69\u201379","journal-title":"Neural Netw"},{"key":"3783_CR55","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.asoc.2020.106516","volume":"106516","author":"H Zhou","year":"2020","unstructured":"Zhou H, Zhang Y, Duan W, Zhao H (2020) Nonlinear systems modelling based on self-organizing fuzzy neural network with hierarchical pruning scheme. Appl Soft Comput 106516:95. https:\/\/doi.org\/10.1016\/j.asoc.2020.106516","journal-title":"Appl Soft Comput"},{"key":"3783_CR56","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/j.neucom.2020.02.035","volume":"398","author":"S Swaminathan","year":"2020","unstructured":"Swaminathan S, Garg D, Kannan R, Andres F (2020) Sparse low rank factorization for deep neural network compression. Neurocomputing 398:185\u2013196","journal-title":"Neurocomputing"},{"issue":"7","key":"3783_CR57","doi-asserted-by":"publisher","first-page":"4561","DOI":"10.1007\/s10489-020-02109-0","volume":"51","author":"C Huang","year":"2021","unstructured":"Huang C, Liu P, Fang L (2021) MXQN: mixed quantization for reducing bit-width of weights and activations in deep convolutional neural networks. Appl Intell 51(7):4561. https:\/\/doi.org\/10.1007\/s10489-020-02109-0","journal-title":"Appl Intell"},{"key":"3783_CR58","doi-asserted-by":"publisher","first-page":"150823","DOI":"10.1109\/ACCESS.2019.2947846","volume":"7","author":"K Guo","year":"2019","unstructured":"Guo K, Xie X, Xu X, Xing X (2019) Compressing by learning in a low-rank and sparse decomposition form. IEEE Access 7:150823. https:\/\/doi.org\/10.1109\/ACCESS.2019.2947846","journal-title":"IEEE Access"},{"issue":"1","key":"3783_CR59","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1109\/TNN.2005.860850","volume":"17","author":"G Indiveri","year":"2006","unstructured":"Indiveri G, Chicca E, Douglas R (2006) A VLSI array of low-power spiking neurons and bistable synapses with spike-timing dependent plasticity. IEEE Trans Neural Netw 17(1):211\u2013221. https:\/\/doi.org\/10.1109\/TNN.2005.860850","journal-title":"IEEE Trans Neural Netw"},{"issue":"11","key":"3783_CR60","doi-asserted-by":"publisher","first-page":"1088","DOI":"10.1109\/TCSII.2015.2456372","volume":"62","author":"X Wu","year":"2015","unstructured":"Wu X, Saxena V, Zhu K, Balagopal S (2015) A CMOS spiking neuron for brain-inspired neural networks with resistive synapses and in situ learning. IEEE Trans Circuits Syst II: Express Br 62(11):1088\u20131092. https:\/\/doi.org\/10.1109\/TCSII.2015.2456372","journal-title":"IEEE Trans Circuits Syst II: Express Br"},{"key":"3783_CR61","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/JEDS.2020.3011409","volume":"8","author":"E Yu","year":"2020","unstructured":"Yu E, Cho S, Roy K, Park BG (2020) A quantum-well charge-trap synaptic transistor with highly linear weight tunability. IEEE J Electron Devices Soc 8:834\u2013840. https:\/\/doi.org\/10.1109\/JEDS.2020.3011409","journal-title":"IEEE J Electron Devices Soc"},{"key":"3783_CR62","doi-asserted-by":"publisher","unstructured":"Cho Y, Lee JY, Yu E, Han JH, Baek MH, Cho S, Park BG (2019) Design and characterization of semi-floating-gate synaptic transistor. Micromachines 10(1). https:\/\/doi.org\/10.3390\/mi10010032","DOI":"10.3390\/mi10010032"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03783-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-03783-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03783-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T04:28:42Z","timestamp":1677472122000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-03783-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,8]]},"references-count":62,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["3783"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-03783-y","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2022,7,8]]},"assertion":[{"value":"17 May 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}