{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T12:47:48Z","timestamp":1774702068265,"version":"3.50.1"},"reference-count":36,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T00:00:00Z","timestamp":1715731200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T00:00:00Z","timestamp":1715731200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100009595","name":"Service Public de Wallonie","doi-asserted-by":"crossref","award":["2010235"],"award-info":[{"award-number":["2010235"]}],"id":[{"id":"10.13039\/501100009595","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>Spiking neural networks (SNNs) are a type of artificial neural networks in which communication between neurons is only made of events, also called spikes. This property allows neural networks to make asynchronous and sparse computations and therefore drastically decrease energy consumption when run on specialized hardware. However, training such networks is known to be difficult, mainly due to the non-differentiability of the spike activation, which prevents the use of classical backpropagation. This is because state-of-the-art SNNs are usually derived from biologically-inspired neuron models, to which are applied machine learning methods for training. Nowadays, research about SNNs focuses on the design of training algorithms whose goal is to obtain networks that compete with their non-spiking version on specific tasks. In this paper, we attempt the symmetrical approach: we modify the dynamics of a well-known, easily trainable type of recurrent neural network (RNN) to make it event-based. This new RNN cell, called the spiking recurrent cell, therefore communicates using events, i.e. spikes, while being completely differen-tiable. Vanilla backpropagation can thus be used to train any network made of such RNN cell. We show that this new network can achieve performance comparable to other types of spiking networks in the MNIST benchmark and its variants, the Fashion-MNIST and the Neuromorphic-MNIST. Moreover, we show that this new cell makes the training of deep spiking networks achievable.<\/jats:p>","DOI":"10.1088\/2634-4386\/ad473b","type":"journal-article","created":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T22:27:50Z","timestamp":1714775270000},"page":"024007","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Spike-based computation using classical recurrent neural networks"],"prefix":"10.1088","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0977-7244","authenticated-orcid":true,"given":"Florent","family":"De Geeter","sequence":"first","affiliation":[]},{"given":"Damien","family":"Ernst","sequence":"additional","affiliation":[]},{"given":"Guillaume","family":"Drion","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2024,5,15]]},"reference":[{"key":"ncead473bbib1","doi-asserted-by":"publisher","first-page":"1659","DOI":"10.1016\/S0893-6080(97)00011-7","article-title":"Networks of spiking neurons: the third generation of neural network models","volume":"10","author":"Maass","year":"1997","journal-title":"Neural Netw."},{"key":"ncead473bbib2","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MM.2018.112130359","article-title":"Loihi: a neuromorphic manycore processor with on-chip learning","volume":"38","author":"Davies","year":"2018","journal-title":"IEEE Micro"},{"key":"ncead473bbib3","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":"ncead473bbib4","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":"ncead473bbib5","first-page":"1724","article-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","author":"Cho","year":"2014"},{"key":"ncead473bbib6","article-title":"On the difficulty of training recurrent neural networks","author":"Pascanu","year":"2013"},{"key":"ncead473bbib7","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"},{"key":"ncead473bbib8","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":"ncead473bbib9","article-title":"Efficient recurrent architectures through activity sparsity and sparse back-propagation through time","author":"Subramoney","year":"2023"},{"key":"ncead473bbib10","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1113\/jphysiol.1952.sp004764","article-title":"A quantitative description of membrane current and its application to conduction and excitation in nerve","volume":"117","author":"Hodgkin","year":"1952","journal-title":"J. Phys."},{"key":"ncead473bbib11","doi-asserted-by":"publisher","first-page":"863","DOI":"10.3390\/brainsci12070863","article-title":"Spiking neural networks and their applications: a review","volume":"12","author":"Yamazaki","year":"2022","journal-title":"Brain Sci."},{"key":"ncead473bbib12","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.neunet.2018.12.002","article-title":"Deep learning in spiking neural networks","volume":"111","author":"Tavanaei","year":"2018","journal-title":"Neural Netw."},{"key":"ncead473bbib13","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":"ncead473bbib14","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":"ncead473bbib15","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1109\/TNNLS.2014.2362542","article-title":"Unsupervised learning of digit recognition using spike-timing-dependent plasticity","volume":"9","author":"Diehl","year":"2015","journal-title":"Front. Comput. Neurosci."},{"key":"ncead473bbib16","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":"ncead473bbib17","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1126\/science.275.5297.213","article-title":"Regulation of synaptic efficacy by coincidence of postsynaptic APs and EPSPs","volume":"275","author":"Markram","year":"1997","journal-title":"Science"},{"key":"ncead473bbib18","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1007\/s11263-014-0788-3","article-title":"Spiking deep convolutional neural networks for energy-efficient object recognition","volume":"113","author":"Cao","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"ncead473bbib19","first-page":"pp 1","article-title":"Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing","author":"Diehl","year":"2015"},{"key":"ncead473bbib20","first-page":"11441","article-title":"Convolutional networks for fast, energy-efficient neuromorphic computing","volume":"113","author":"Esser","year":"2016"},{"key":"ncead473bbib21","article-title":"SpikeProp: backpropagation for networks of spiking neurons","author":"Boht\u00e9","year":"2000"},{"key":"ncead473bbib22","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1162\/NECO_a_00396","article-title":"Supervised learning in multilayer spiking neural networks","volume":"25","author":"Sporea","year":"2013","journal-title":"Neural Comput."},{"key":"ncead473bbib23","article-title":"Spiking deep networks with lif neurons","author":"Hunsberger","year":"2015"},{"key":"ncead473bbib24","doi-asserted-by":"publisher","first-page":"1514","DOI":"10.1162\/neco_a_01086","article-title":"Superspike: supervised learning in multi-layer spiking neural networks","volume":"30","author":"Zenke","year":"2018","journal-title":"Neural Comput."},{"key":"ncead473bbib25","first-page":"p 31","article-title":"SLAYER: spike layer error reassignment in time","author":"Bam Shrestha","year":"2018"},{"key":"ncead473bbib26","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":"Haeng Lee","year":"2016","journal-title":"Front. Neurosci."},{"key":"ncead473bbib27","first-page":"p 31","article-title":"Gradient descent for spiking neural networks","author":"Huh","year":"2018"},{"key":"ncead473bbib28","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0252676","article-title":"A bio-inspired bistable recurrent cell allows for long-lasting memory","volume":"16","author":"Vecoven","year":"2021","journal-title":"PLoS One"},{"key":"ncead473bbib29","article-title":"Training spiking neural networks using lessons from deep learning","author":"Eshraghian","year":"2021"},{"key":"ncead473bbib30","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":"Li","year":"2012","journal-title":"IEEE Signal Process. Mag."},{"key":"ncead473bbib31","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2015.00437)","article-title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"ncead473bbib32","doi-asserted-by":"publisher","first-page":"437","DOI":"10.3389\/fnins.2015.00437","article-title":"Converting static image datasets to spiking neuromorphic datasets using saccades","volume":"9","author":"Orchard","year":"2015","journal-title":"Front. Neurosci."},{"key":"ncead473bbib33","article-title":"Tonic: event-based datasets and transformations","author":"Lenz","year":"2021"},{"key":"ncead473bbib34","first-page":"1","article-title":"The FPGA hardware implementation of the gated recurrent unit architecture","volume":"2021","author":"Saad Zaghloul","year":"2021","journal-title":"SoutheastCon"},{"key":"ncead473bbib35","doi-asserted-by":"publisher","first-page":"4","DOI":"10.17577\/IJERTV12IS040268","article-title":"Simulation and high level synthesis of gated recurrent unit for field programmable gate array","volume":"12","author":"Derick","year":"2018","journal-title":"Int. J. Eng. Res. Technol."},{"key":"ncead473bbib36","doi-asserted-by":"publisher","first-page":"1367","DOI":"10.1109\/JPROC.2014.2313954","article-title":"Neuromorphic electronic circuits for building autonomous cognitive systems","volume":"102","author":"Chicca","year":"2014","journal-title":"Proc. IEEE"}],"container-title":["Neuromorphic Computing and Engineering"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad473b","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad473b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad473b","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad473b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad473b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad473b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad473b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad473b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T09:38:16Z","timestamp":1715765896000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ad473b"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,15]]},"references-count":36,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,5,15]]},"published-print":{"date-parts":[[2024,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2634-4386\/ad473b","relation":{},"ISSN":["2634-4386"],"issn-type":[{"value":"2634-4386","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,15]]},"assertion":[{"value":"Spike-based computation using classical recurrent neural networks","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":"2023-12-15","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-05-03","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-05-15","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}