{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T18:52:55Z","timestamp":1778179975417,"version":"3.51.4"},"reference-count":44,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T00:00:00Z","timestamp":1672963200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T00:00:00Z","timestamp":1672963200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"crossref","award":["559730"],"award-info":[{"award-number":["559730"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"crossref"}]},{"name":"CHIST-ERA UNICO project"},{"name":"EU: ERC-2017-COG project IONOS","award":["773228"],"award-info":[{"award-number":["773228"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Neuromorph. Comput. Eng."],"published-print":{"date-parts":[[2023,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Spiking neural networks (SNNs) are gaining attention due to their energy-efficient computing ability, making them relevant for implementation on low-power neuromorphic hardware. Their biological plausibility has permitted them to benefit from unsupervised learning with bio-inspired plasticity rules, such as spike timing-dependent plasticity (STDP). However, standard STDP has some limitations that make it challenging to implement on hardware. In this paper, we propose a convolutional SNN (CSNN) integrating single-spike integrate-and-fire (SSIF) neurons and trained for the first time with voltage-dependent synaptic plasticity (VDSP), a novel unsupervised and local plasticity rule developed for the implementation of STDP on memristive-based neuromorphic hardware. We evaluated the CSNN on the TIDIGITS dataset, where, helped by our sound preprocessing pipeline, we obtained a performance better than the state of the art, with a mean accuracy of 99.43%. Moreover, the use of SSIF neurons, coupled with time-to-first-spike (TTFS) encoding, results in a sparsely activated model, as we recorded a mean of 5036 spikes per input over the 172\u2009580 neurons of the network. This makes the proposed CSNN promising for the development of models that are extremely efficient in energy. We also demonstrate the efficiency of VDSP on the MNIST dataset, where we obtained results comparable to the state of the art, with an accuracy of 98.56%. Our adaptation of VDSP for SSIF neurons introduces a depression factor that has been very effective at reducing the number of training samples needed, and hence, training time, by a factor of two and more, with similar performance.<\/jats:p>","DOI":"10.1088\/2634-4386\/acad98","type":"journal-article","created":{"date-parts":[[2022,12,21]],"date-time":"2022-12-21T22:25:20Z","timestamp":1671661520000},"page":"014001","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Unsupervised and efficient learning in sparsely activated convolutional spiking neural networks enabled by voltage-dependent synaptic plasticity"],"prefix":"10.1088","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6992-3175","authenticated-orcid":true,"given":"Gaspard","family":"Goupy","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0517-5278","authenticated-orcid":true,"given":"Alexandre","family":"Juneau-Fecteau","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9210-2826","authenticated-orcid":true,"given":"Nikhil","family":"Garg","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6730-0794","authenticated-orcid":true,"given":"Ismael","family":"Balafrej","sequence":"additional","affiliation":[]},{"given":"Fabien","family":"Alibart","sequence":"additional","affiliation":[]},{"given":"Luc","family":"Frechette","sequence":"additional","affiliation":[]},{"given":"Dominique","family":"Drouin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0311-8840","authenticated-orcid":true,"given":"Yann","family":"Beilliard","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2023,1,6]]},"reference":[{"key":"nceacad98bib1","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":"nceacad98bib2","first-page":"pp 844","article-title":"Medical image classification with convolutional neural network","author":"Li","year":"2014"},{"key":"nceacad98bib3","article-title":"Conditional image generation with PixelCNN decoders","volume":"vol 29","author":"van den Oord","year":"2016"},{"key":"nceacad98bib4","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"SegNet: a deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"nceacad98bib5","first-page":"pp 1547","article-title":"A convolutional neural network approach for acoustic scene classification","author":"Valenti","year":"2017"},{"key":"nceacad98bib6","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1109\/LSP.2017.2657381","article-title":"Deep convolutional neural networks and data augmentation for environmental sound classification","volume":"24","author":"Salamon","year":"2017","journal-title":"IEEE Signal Process. Lett."},{"key":"nceacad98bib7","first-page":"pp 432","article-title":"Acoustic anomaly detection using convolutional autoencoders in industrial processes","author":"Duman","year":"2020","edition":"ed"},{"key":"nceacad98bib8","first-page":"pp 4438","article-title":"The McCulloch-Pitts model","volume":"vol 6","author":"Hayman","year":"1999"},{"key":"nceacad98bib9","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1142\/S0129065709002002","article-title":"Spiking neural networks","volume":"19","author":"Ghosh-Dastidar","year":"2009","journal-title":"Int. J. Neural Syst."},{"key":"nceacad98bib10","doi-asserted-by":"publisher","first-page":"508","DOI":"10.3389\/fnins.2016.00508","article-title":"Training deep spiking neural networks using backpropagation","volume":"10","author":"Lee","year":"2016","journal-title":"Front. Neurosci."},{"key":"nceacad98bib11","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.neunet.2017.12.005","article-title":"STDP-based spiking deep convolutional neural networks for object recognition","volume":"99","author":"Kheradpisheh","year":"2018","journal-title":"Neural Netw."},{"key":"nceacad98bib12","doi-asserted-by":"publisher","first-page":"1319","DOI":"10.1609\/aaai.v33i01.33011319","article-title":"TDSNN: from deep neural networks to deep spike neural networks with temporal-coding","volume":"33","author":"Zhang","year":"2019","journal-title":"Proc. AAAI Conf. Artificial Intelligence"},{"key":"nceacad98bib13","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1109\/TCDS.2018.2833071","article-title":"Deep spiking convolutional neural network trained with unsupervised spike-timing-dependent plasticity","volume":"11","author":"Lee","year":"2019","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"nceacad98bib14","doi-asserted-by":"publisher","first-page":"331","DOI":"10.3389\/fnins.2018.00331","article-title":"Spatio-temporal backpropagation for training high-performance spiking neural networks","volume":"12","author":"Wu","year":"2018","journal-title":"Front. Neurosci."},{"key":"nceacad98bib15","article-title":"Spike-train level backpropagation for training deep recurrent spiking neural networks","volume":"vol 32","author":"Zhang","year":"2019"},{"key":"nceacad98bib16","doi-asserted-by":"publisher","first-page":"324","DOI":"10.3389\/fnins.2017.00324","article-title":"Event-driven random back-propagation: Enabling neuromorphic deep learning machines","volume":"11","author":"Neftci","year":"2017","journal-title":"Front. Neurosci."},{"key":"nceacad98bib17","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1109\/MSP.2019.2931595","article-title":"Surrogate gradient learning in spiking neural networks: bringing the power of gradient-based optimization to spiking neural networks","volume":"36","author":"Neftci","year":"2019","journal-title":"IEEE Signal Process. Mag."},{"key":"nceacad98bib18","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1146\/annurev.neuro.31.060407.125639","article-title":"Spike timing-dependent plasticity: a Hebbian learning rule","volume":"31","author":"Caporale","year":"2008","journal-title":"Annu. Rev. Neurosci."},{"key":"nceacad98bib19","author":"Hebb","year":"1949"},{"key":"nceacad98bib20","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.neucom.2018.11.014","article-title":"BP-STDP: approximating backpropagation using spike timing dependent plasticity","volume":"330","author":"Tavanaei","year":"2018","journal-title":"Neurocomputing"},{"key":"nceacad98bib21","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0204596","article-title":"Unsupervised speech recognition through spike-timing-dependent plasticity in a convolutional spiking neural network","volume":"13","author":"Dong","year":"2018","journal-title":"PLoS One"},{"key":"nceacad98bib22","first-page":"pp 1","article-title":"Multi-layered spiking neural network with target timestamp threshold adaptation and STDP","author":"Falez","year":"2019"},{"key":"nceacad98bib23","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2022.983950","article-title":"Voltage-dependent synaptic plasticity (VDSP): Unsupervised probabilistic Hebbian plasticity rule based on neurons membrane potential","volume":"16","author":"Garg","year":"2022","journal-title":"Front. Neurosci."},{"key":"nceacad98bib24","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202000137","article-title":"Hardware implementation of neuromorphic computing using large-scale memristor crossbar arrays","volume":"3","author":"Li","year":"2021","journal-title":"Adv. Intell. Syst."},{"key":"nceacad98bib25","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1038\/381520a0","article-title":"Speed of processing in the human visual system","volume":"381","author":"Thorpe","year":"1996","journal-title":"Nature"},{"key":"nceacad98bib26","article-title":"TIDIGITS","author":"Leonard","year":"1993"},{"key":"nceacad98bib27","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":"nceacad98bib28","author":"","year":"2022"},{"key":"nceacad98bib29","doi-asserted-by":"publisher","first-page":"329","DOI":"10.2307\/1417526","article-title":"The relation of pitch to frequency: a revised scale","volume":"53","author":"Stevens","year":"1940","journal-title":"Am. J. Psychol."},{"key":"nceacad98bib30","doi-asserted-by":"publisher","first-page":"4693","DOI":"10.1007\/s11063-021-10562-2","article-title":"A survey of encoding techniques for signal processing in spiking neural networks","volume":"53","author":"Auge","year":"2021","journal-title":"Neural Process. Lett."},{"key":"nceacad98bib31","first-page":"pp 1","article-title":"T2FSNN: deep spiking neural networks with time-to-first-spike coding","author":"Park","year":"2020"},{"key":"nceacad98bib32","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065720500276","article-title":"Temporal backpropagation for spiking neural networks with one spike per neuron","volume":"30","author":"Kheradpisheh","year":"2020","journal-title":"Int. J. Neural Syst."},{"key":"nceacad98bib33","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1152\/jn.2001.85.3.1039","article-title":"Temporal coding of contrast in primary visual cortex: when, what and why","volume":"85","author":"Reich","year":"2001","journal-title":"J. Neurophysiol."},{"key":"nceacad98bib34","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1007\/s10827-005-1739-3","article-title":"Encoding stimulus information by spike numbers and mean response time in primary auditory cortex","volume":"19","author":"Nelken","year":"2005","journal-title":"J. Comput. Neurosci."},{"key":"nceacad98bib35","doi-asserted-by":"publisher","first-page":"7497","DOI":"10.1523\/JNEUROSCI.6044-08.2009","article-title":"A second function of gamma frequency oscillations: an E%-max Winner-take-all mechanism selects which cells fire","volume":"29","author":"Almeida","year":"2009","journal-title":"J. Neurosci."},{"key":"nceacad98bib36","article-title":"SLAYER: spike layer error reassignment in time","volume":"vol 31","author":"Shrestha","year":"2018"},{"key":"nceacad98bib37","first-page":"pp 8917","article-title":"Motif-topology and reward-learning improved spiking neural network for efficient multi-sensory integration","author":"Jia","year":"2022"},{"key":"nceacad98bib38","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2021.654786","article-title":"Neuronal-plasticity and reward-propagation improved recurrent spiking neural networks","volume":"15","author":"Jia","year":"2021","journal-title":"Front. Neurosci."},{"key":"nceacad98bib39","first-page":"pp 1","article-title":"A biologically plausible speech recognition framework based on spiking neural networks","author":"Wu","year":"2018"},{"key":"nceacad98bib40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TNNLS.2021.3085966","article-title":"Tuning convolutional spiking neural network with biologically plausible reward propagation","volume":"33","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"nceacad98bib41","doi-asserted-by":"publisher","first-page":"e31","DOI":"10.1371\/journal.pcbi.0030031","article-title":"Unsupervised learning of visual features through spike timing dependent plasticity","volume":"3","author":"Masquelier","year":"2007","journal-title":"PLoS Comput. Biol."},{"key":"nceacad98bib42","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1038\/nature09086","article-title":"Sensitivity to perturbations in vivo implies high noise and suggests rate coding in cortex","volume":"466","author":"London","year":"2010","journal-title":"Nature"},{"key":"nceacad98bib43","doi-asserted-by":"publisher","first-page":"1255","DOI":"10.1007\/s11063-021-10680-x","article-title":"BS4NN: binarized spiking neural networks with temporal coding and learning","volume":"54","author":"Kheradpisheh","year":"2022","journal-title":"Neural Process. Lett."},{"key":"nceacad98bib44","doi-asserted-by":"publisher","first-page":"6178","DOI":"10.1109\/TNNLS.2018.2826721","article-title":"First-spike-based visual categorization using reward-modulated STDP","volume":"29","author":"Mozafari","year":"2018","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."}],"container-title":["Neuromorphic Computing and Engineering"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acad98","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acad98\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acad98","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acad98\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acad98\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acad98\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acad98\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acad98\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T14:05:07Z","timestamp":1673013907000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acad98"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,6]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,1,6]]},"published-print":{"date-parts":[[2023,3,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2634-4386\/acad98","relation":{},"ISSN":["2634-4386"],"issn-type":[{"value":"2634-4386","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,6]]},"assertion":[{"value":"Unsupervised and efficient learning in sparsely activated convolutional spiking neural networks enabled by voltage-dependent synaptic 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 2023 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2022-09-30","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-12-21","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-01-06","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}