{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T23:27:13Z","timestamp":1778110033858,"version":"3.51.4"},"reference-count":128,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1652159"],"award-info":[{"award-number":["1652159"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1823366 (EN)"],"award-info":[{"award-number":["1823366 (EN)"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008273","name":"Novartis Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008273","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. IEEE"],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1109\/jproc.2020.3045625","type":"journal-article","created":{"date-parts":[[2021,1,9]],"date-time":"2021-01-09T18:38:16Z","timestamp":1610217496000},"page":"935-950","source":"Crossref","is-referenced-by-count":72,"title":["Brain-Inspired Learning on Neuromorphic Substrates"],"prefix":"10.1109","volume":"109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1883-644X","authenticated-orcid":false,"given":"Friedemann","family":"Zenke","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0332-3273","authenticated-orcid":false,"given":"Emre O.","family":"Neftci","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2013.11.006"},{"key":"ref38","author":"izhikevich","year":"2007","journal-title":"Dynamical Systems in Neuroscience The Geometry of Excitability and Bursting"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref32","first-page":"78","article-title":"A pulse-coded communications infrastructure for neuromorphic systems","author":"deiss","year":"1998","journal-title":"Pulsed Neural Networks"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/72.217193"},{"key":"ref30","author":"sterling","year":"2017","journal-title":"Principles of Neural Design"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2015.7402491"},{"key":"ref36","article-title":"Continual lifelong learning with neural networks: A review","author":"parisi","year":"2018","journal-title":"arXiv 1802 07569"},{"key":"ref35","article-title":"Continual learning through synaptic intelligence","author":"zenke","year":"2017","journal-title":"arXiv 1703 04200"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-019-0520-2"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-17236-y"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2018.06.010"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2019.2931595"},{"key":"ref22","first-page":"8721","article-title":"Dendritic cortical microcircuits approximate the backpropagation algorithm","author":"sacramento","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-0187-0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3389\/fncir.2015.00085"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.4098-12.2013"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1126\/science.aab4113"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.22901"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.28295"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2017.08.020"},{"key":"ref50","article-title":"A practical sparse approximation for real time recurrent learning","author":"menick","year":"2020","journal-title":"arXiv 2006 07232"},{"key":"ref51","article-title":"Deep rewiring: Training very sparse deep networks","author":"bellec","year":"2017","journal-title":"arXiv 1711 05136"},{"key":"ref59","article-title":"SN: A simulator for connectionist models","volume":"88","author":"bottou","year":"1988","journal-title":"Proc NeuroNimes"},{"key":"ref58","first-page":"5595","article-title":"Automatic differentiation in machine learning: A survey","volume":"18","author":"baydin","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972078"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898717761"},{"key":"ref55","first-page":"6336","article-title":"Finding trainable sparse networks through neural tangent transfer","volume":"1","author":"liu","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref54","article-title":"Rigging the lottery: Making all tickets winners","author":"evci","year":"2019","journal-title":"arXiv 1911 11134"},{"key":"ref53","article-title":"Pruning neural networks without any data by iteratively conserving synaptic flow","author":"tanaka","year":"2020","journal-title":"arXiv 2006 05467"},{"key":"ref52","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","author":"frankle","year":"2018","journal-title":"arXiv 1803 03635"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/5.58356"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/science.1254642"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0097-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2011.00073"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.112130359"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41583-020-0277-3"},{"key":"ref49","article-title":"Approximating real-time recurrent learning with random kronecker factors","author":"mujika","year":"2018","journal-title":"arXiv 1805 10842"},{"key":"ref7","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/nn1643"},{"key":"ref46","first-page":"1","article-title":"Stable recurrent models","author":"miller","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref48","article-title":"On the variance of unbiased online recurrent optimization","author":"cooijmans","year":"2019","journal-title":"arXiv 1902 02405"},{"key":"ref47","article-title":"Unbiased online recurrent optimization","author":"tallec","year":"2017","journal-title":"arXiv 1702 05043"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966124"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2009.5118408"},{"key":"ref44","first-page":"1","article-title":"A unified framework of online learning algorithms for training recurrent neural networks","volume":"21","author":"marschall","year":"2019","journal-title":"J Mach Learn Res"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_2"},{"key":"ref127","article-title":"Training neural networks with local error signals","author":"n\u00f8kland","year":"2019","journal-title":"arXiv 1901 06656"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2019.00018"},{"key":"ref125","first-page":"976","article-title":"Deep learning without weight transport","author":"akrout","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1994.374486"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog0901_7"},{"key":"ref72","article-title":"Optimized spiking neurons can classify images with high accuracy through temporal coding with two spikes","author":"st\u00f6ckl","year":"2020","journal-title":"arXiv 2002 00860"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1905926116"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2018.00608"},{"key":"ref70","article-title":"Efficient computation in adaptive artificial spiking neural networks","author":"zambrano","year":"2017","journal-title":"arXiv 1710 04838"},{"key":"ref76","first-page":"1440","article-title":"Gradient descent for spiking neural networks","volume":"31","author":"huh","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3407197.3407225"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2019.2935234"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s10827-016-0599-3"},{"key":"ref78","article-title":"The remarkable robustness of surrogate gradient learning for instilling complex function in spiking neural networks","author":"zenke","year":"2020","journal-title":"BioRxiv"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107447615"},{"key":"ref60","article-title":"Theano: A Python framework for fast computation of mathematical expressions","author":"al-rfou","year":"2016","journal-title":"arXiv 1605 02688"},{"key":"ref62","article-title":"Automatic differentiation in Pytorch","author":"paszke","year":"2017","journal-title":"Proc NIPS Autodiff Workshop"},{"key":"ref61","author":"abadi","year":"2015","journal-title":"TensorFlow Large-Scale Machine Learning on Heterogeneous Systems"},{"key":"ref63","article-title":"Dynamic automatic differentiation of GPU broadcast kernels","author":"revels","year":"2018","journal-title":"arXiv 1810 08297"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-006-0042-z"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1038\/nn.3431"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1038\/nn.4241"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2018.00774"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.12.002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2018.00891"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2017.00682"},{"key":"ref1","author":"mead","year":"1989","journal-title":"Analog VLSI and Neural Systems"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS48895.2020.9073998"},{"key":"ref95","article-title":"SpikeGrad: An ANN-equivalent computation model for implementing backpropagation with spikes","author":"christian thiele","year":"2019","journal-title":"arXiv 1906 00851"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/s10827-007-0038-6"},{"key":"ref94","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"arXiv 1802 08435"},{"key":"ref107","article-title":"An efficient and perceptually motivated auditory neural encoding and decoding algorithm for spiking neural networks","author":"pan","year":"2019","journal-title":"arXiv 1909 01302"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.43299"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhl152"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.43299"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.3389\/fncir.2018.00053"},{"key":"ref91","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"warden","year":"2018","journal-title":"arXiv 1804 03209"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0161335"},{"key":"ref90","article-title":"The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks","author":"cramer","year":"2019","journal-title":"arXiv 1910 07407"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1162\/089976601300014321"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2020.3032058"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00182"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/s00422-011-0435-9"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1604850113"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2009.07.018"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-017-01827-3"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2020.00119"},{"key":"ref97","article-title":"Online spatio-temporal learning in deep neural networks","author":"bohnstingl","year":"2020","journal-title":"arXiv 2007 12723"},{"key":"ref10","first-page":"419","article-title":"Spikeprop: Backpropagation for networks of spiking neurons","author":"bohte","year":"2000","journal-title":"Proc ESANN"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.6.1318"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1037\/h0042519"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2014.00038"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00790"},{"key":"ref15","first-page":"1412","article-title":"Slayer: Spike layer error reassignment in time","author":"shrestha","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms7922"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2016.00508"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.3389\/neuro.11.005.2008"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms6319"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01086"},{"key":"ref81","first-page":"1197","article-title":"Learning curves for stochastic gradient descent in linear feedforward networks","author":"werfel","year":"2004","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","first-page":"795","article-title":"Long short-term memory and learning-to-learn in networks of spiking neurons","author":"bellec","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2013.07.036"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2020.00424"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2014.00076"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1162\/089976606775093909"},{"key":"ref113","article-title":"Training spiking multi-layer networks with surrogate gradients on an analog neuromorphic substrate","author":"cramer","year":"2020","journal-title":"arXiv 2006 07239"},{"key":"ref116","author":"amit","year":"1992","journal-title":"Modeling brain function The world of attractor neural networks"},{"key":"ref80","article-title":"VOWEL: A local online learning rule for recurrent networks of probabilistic spiking winner-take-all circuits","author":"jang","year":"2020","journal-title":"arXiv 2004 09416"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00091"},{"key":"ref89","article-title":"SNIP: Single-shot network pruning based on connection sensitivity","author":"lee","year":"2019","journal-title":"arXiv 1810 02340"},{"key":"ref121","author":"grossberg","year":"1987","journal-title":"The Adaptive Brain"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.03.003"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms13276"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2019.00357"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TBCAS.2017.2759700"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2572164"},{"key":"ref88","article-title":"CondenseNet: An efficient DenseNet using learned group convolutions","volume":"3","author":"huang","year":"2017","journal-title":"arXiv 1711 09224"}],"container-title":["Proceedings of the IEEE"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5\/9420072\/9317744-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5\/9420072\/09317744.pdf?arnumber=9317744","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:55:57Z","timestamp":1649444157000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9317744\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5]]},"references-count":128,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/jproc.2020.3045625","relation":{},"ISSN":["0018-9219","1558-2256"],"issn-type":[{"value":"0018-9219","type":"print"},{"value":"1558-2256","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5]]}}}