{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T01:21:42Z","timestamp":1771464102172,"version":"3.50.1"},"reference-count":53,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T00:00:00Z","timestamp":1715040000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T00:00:00Z","timestamp":1715040000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000143","name":"Division of Computing and Communication Foundations","doi-asserted-by":"crossref","award":["1955815"],"award-info":[{"award-number":["1955815"]}],"id":[{"id":"10.13039\/100000143","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000015","name":"US Department of Energy","doi-asserted-by":"crossref","award":["DE-SC0021562"],"award-info":[{"award-number":["DE-SC0021562"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Neuromorph. Comput. Eng."],"published-print":{"date-parts":[[2024,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Spike-timing-dependent plasticity (STDP) is an unsupervised learning mechanism for spiking neural networks that has received significant attention from the neuromorphic hardware community. However, scaling such local learning techniques to deeper networks and large-scale tasks has remained elusive. In this work, we investigate a Deep-STDP framework where a rate-based convolutional network, that can be deployed in a neuromorphic setting, is trained in tandem with pseudo-labels generated by the STDP clustering process on the network outputs. We achieve 24.56% higher accuracy and 3.5\u2009\u00d7 faster convergence speed at iso-accuracy on a 10-class subset of the Tiny ImageNet dataset in contrast to a <jats:italic>k<\/jats:italic>-means clustering approach.<\/jats:p>","DOI":"10.1088\/2634-4386\/ad3a95","type":"journal-article","created":{"date-parts":[[2024,4,4]],"date-time":"2024-04-04T22:25:55Z","timestamp":1712269555000},"page":"024004","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Deep unsupervised learning using spike-timing-dependent plasticity"],"prefix":"10.1088","volume":"4","author":[{"given":"Sen","family":"Lu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5545-4494","authenticated-orcid":true,"given":"Abhronil","family":"Sengupta","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2024,5,7]]},"reference":[{"key":"ncead3a95bib1","first-page":"p 29","article-title":"K-means clustering via principal component analysis","author":"Ding","year":"2004"},{"key":"ncead3a95bib2","first-page":"pp 1","article-title":"Visual categorization with bags of keypoints","volume":"vol 1","author":"Csurka","year":"2004"},{"key":"ncead3a95bib3","first-page":"pp 132","article-title":"Deep clustering for unsupervised learning of visual features","author":"Caron","year":"2018"},{"key":"ncead3a95bib4","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"Radford","year":"2015"},{"key":"ncead3a95bib5","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ncead3a95bib6","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ncead3a95bib7","doi-asserted-by":"publisher","first-page":"95","DOI":"10.3389\/fnins.2019.00095","article-title":"Going deeper in spiking neural networks: Vgg and residual architectures","volume":"13","author":"Sengupta","year":"2019","journal-title":"Front. Neurosci."},{"key":"ncead3a95bib8","doi-asserted-by":"publisher","first-page":"911","DOI":"10.1109\/JPROC.2021.3067593","article-title":"Advancing neuromorphic computing with loihi: a survey of results and outlook","volume":"109","author":"Davies","year":"2021","journal-title":"Proc. IEEE"},{"key":"ncead3a95bib9","doi-asserted-by":"publisher","first-page":"99","DOI":"10.3389\/fncom.2015.00099","article-title":"Unsupervised learning of digit recognition using spike-timing-dependent plasticity","volume":"9","author":"Diehl","year":"2015","journal-title":"Front. Comput. Neurosci."},{"key":"ncead3a95bib10","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1063\/5.0064860","article-title":"Intrinsic synaptic plasticity of ferroelectric field effect transistors for online learning","volume":"119","author":"Saha","year":"2021","journal-title":"Appl. Phys. Lett."},{"key":"ncead3a95bib11","first-page":"pp 1","article-title":"Neuromorphic nearest neighbor search using intel\u2019s pohoiki springs","author":"Frady","year":"2020"},{"key":"ncead3a95bib12","first-page":"2012","article-title":"Unsupervised feature learning and deep learning: a review and new perspectives","volume":"1","author":"Bengio","year":"2012","journal-title":"CoRR"},{"key":"ncead3a95bib13","first-page":"pp 322","article-title":"Unsupervised learning based on artificial neural network: a review","author":"Dike","year":"2018"},{"key":"ncead3a95bib14","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","article-title":"Least squares quantization in pcm","volume":"28","author":"Lloyd","year":"1982","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ncead3a95bib15","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1109\/3477.764879","article-title":"Genetic k-means algorithm","volume":"29","author":"Krishna","year":"1999","journal-title":"IEEE Trans. Syst. Man Cybern. B"},{"key":"ncead3a95bib16","first-page":"pp 1027","article-title":"K-means++ the advantages of careful seeding","author":"Arthur","year":"2007"},{"key":"ncead3a95bib17","first-page":"pp 61","article-title":"Medical image segmentation using k-means clustering and improved watershed algorithm","author":"Ng","year":"2006"},{"key":"ncead3a95bib18","doi-asserted-by":"publisher","first-page":"1200","DOI":"10.1016\/j.eswa.2006.12.025","article-title":"A recommender system using GA K-means clustering in an online shopping market","volume":"34","author":"Kim","year":"2008","journal-title":"Expert Syst. Appl."},{"key":"ncead3a95bib19","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"ncead3a95bib20","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":"ncead3a95bib21","first-page":"p 10\u2009684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"ncead3a95bib22","article-title":"Optimizing the latent space of generative networks","author":"Bojanowski","year":"2017"},{"key":"ncead3a95bib23","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ncead3a95bib24","first-page":"pp 52","article-title":"Stacked convolutional auto-encoders for hierarchical feature extraction","volume":"vol 21","author":"Masci","year":"2011"},{"key":"ncead3a95bib25","first-page":"pp 1","article-title":"Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing","author":"Diehl","year":"2015"},{"key":"ncead3a95bib26","doi-asserted-by":"publisher","first-page":"272","DOI":"10.3389\/fnins.2013.00272","article-title":"Event-driven contrastive divergence for spiking neuromorphic systems","volume":"7","author":"Neftci","year":"2014","journal-title":"Front. Neurosci."},{"key":"ncead3a95bib27","doi-asserted-by":"publisher","first-page":"435","DOI":"10.3389\/fnins.2018.00435","article-title":"Training deep spiking convolutional neural networks with stdp-based unsupervised pre-training followed by supervised fine-tuning","volume":"12","author":"Lee","year":"2018","journal-title":"Front. Neurosci."},{"key":"ncead3a95bib28","doi-asserted-by":"publisher","first-page":"1377","DOI":"10.1109\/TCYB.2018.2801476","article-title":"Event-driven continuous stdp learning with deep structure for visual pattern recognition","volume":"49","author":"Liu","year":"2019","journal-title":"IEEE Trans. Cybern."},{"key":"ncead3a95bib29","doi-asserted-by":"publisher","first-page":"24","DOI":"10.3389\/fncom.2018.00024","article-title":"Unsupervised feature learning with winner-takes-all based stdp","volume":"12","author":"Ferr\u00e9","year":"2018","journal-title":"Front. Comput. Neurosci."},{"key":"ncead3a95bib30","doi-asserted-by":"publisher","first-page":"424","DOI":"10.3389\/fnins.2020.00424","article-title":"Synaptic plasticity dynamics for deep continuous local learning (DECOLLE)","volume":"14","author":"Kaiser","year":"2020","journal-title":"Front. Neurosci."},{"key":"ncead3a95bib31","doi-asserted-by":"publisher","first-page":"24","DOI":"10.3389\/fncom.2017.00024","article-title":"Equilibrium propagation: bridging the gap between energy-based models and backpropagation","volume":"11","author":"Scellier","year":"2017","journal-title":"Front. Comput. Neurosci."},{"key":"ncead3a95bib32","article-title":"Sequence learning using equilibrium propagation","author":"Bal","year":"2022"},{"key":"ncead3a95bib33","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.isci.2021.102222","article-title":"Eqspike: spike-driven equilibrium propagation for neuromorphic implementations","volume":"24","author":"Martin","year":"2021","journal-title":"iScience"},{"key":"ncead3a95bib34","article-title":"Deep equilibrium models","volume":"vol 32","author":"Bai","year":"2019"},{"key":"ncead3a95bib35","first-page":"pp 14516","article-title":"Training feedback spiking neural networks by implicit differentiation on the equilibrium state","volume":"vol 34","author":"Xiao","year":"2021"},{"key":"ncead3a95bib36","article-title":"SpikingBERT: distilling BERT to train spiking language models using implicit differentiation","author":"Bal","year":"2023"},{"key":"ncead3a95bib37","first-page":"pp 69","article-title":"Unsupervised learning of visual representations by solving jigsaw puzzles","author":"Noroozi","year":"2016"},{"key":"ncead3a95bib38","doi-asserted-by":"publisher","DOI":"10.1002\/aelm.201900060","article-title":"Artificial neural network (ANN) to spiking neural network (SNN) converters based on diffusive memristors","volume":"5","author":"Midya","year":"2019","journal-title":"Adv. Electron. Mater."},{"key":"ncead3a95bib39","doi-asserted-by":"publisher","first-page":"535","DOI":"10.3389\/fnins.2020.00535","article-title":"Exploring the connection between binary and spiking neural networks","volume":"14","author":"Lu","year":"2020","journal-title":"Front. Neurosci."},{"key":"ncead3a95bib40","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2022.838523","article-title":"Neuroevolution guided hybrid spiking neural network training","volume":"16","author":"Lu","year":"2022","journal-title":"Front. Neurosci."},{"key":"ncead3a95bib41","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2023.1141701","article-title":"High-accuracy deep ANN-to-SNN conversion using quantization-aware training framework and calcium-gated bipolar leaky integrate and fire neuron","volume":"17","author":"Gao","year":"2023","journal-title":"Front. Neurosci."},{"key":"ncead3a95bib42","article-title":"Long short-term memory and learning-to-learn in networks of spiking neurons","volume":"vol 31","author":"Bellec","year":"2018"},{"key":"ncead3a95bib43","article-title":"DIET-SNN: direct input encoding with leakage and threshold optimization in deep spiking neural networks","author":"Rathi","year":"2020"},{"key":"ncead3a95bib44","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1146\/annurev.neuro.31.060407.125639","article-title":"Spike timing\u2013dependent plasticity: a hebbian learning rule","volume":"31","author":"Caporale","year":"2008","journal-title":"Annu. Rev. Neurosci."},{"key":"ncead3a95bib45","doi-asserted-by":"publisher","first-page":"89","DOI":"10.3389\/fninf.2018.00089","article-title":"Bindsnet: a machine learning-oriented spiking neural networks library in python","volume":"12","author":"Hazan","year":"2018","journal-title":"Front. Neuroinf."},{"key":"ncead3a95bib46","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","article-title":"The mnist database of handwritten digit images for machine learning research","volume":"29","author":"Deng","year":"2012","journal-title":"IEEE Signal Process. Mag."},{"key":"ncead3a95bib47","first-page":"pp 248","article-title":"ImageNet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"ncead3a95bib48","first-page":"pp 649","article-title":"Colorful image colorization","volume":"vol 14","author":"Zhang","year":"2016"},{"key":"ncead3a95bib49","volume":"vol 191","author":"Amari","year":"2000"},{"key":"ncead3a95bib50","first-page":"pp 1032","article-title":"Universal statistics of fisher information in deep neural networks: mean field approach","author":"Karakida","year":"2019"},{"key":"ncead3a95bib51","article-title":"Exploring temporal information dynamics in spiking neural networks","author":"Kim","year":"2022"},{"key":"ncead3a95bib52","first-page":"1","article-title":"Visualizing higher-layer features of a deep network","volume":"1341","author":"Erhan","year":"2009","journal-title":"Univ. Montreal"},{"key":"ncead3a95bib53","article-title":"Learning both weights and connections for efficient neural network","volume":"vol 28","author":"Han","year":"2015"}],"container-title":["Neuromorphic Computing and Engineering"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad3a95","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad3a95\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad3a95","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad3a95\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad3a95\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad3a95\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad3a95\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad3a95\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T07:55:30Z","timestamp":1715068530000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad3a95"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,7]]},"references-count":53,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,5,7]]},"published-print":{"date-parts":[[2024,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2634-4386\/ad3a95","relation":{},"ISSN":["2634-4386"],"issn-type":[{"value":"2634-4386","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,7]]},"assertion":[{"value":"Deep unsupervised learning using spike-timing-dependent plasticity","name":"article_title","label":"Article Title"},{"value":"Neuromorphic Computing and Engineering","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-10-22","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-04-04","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-05-07","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}