{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T10:15:18Z","timestamp":1778408118518,"version":"3.51.4"},"reference-count":67,"publisher":"MIT Press - Journals","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2018,6]]},"abstract":"<jats:p> A vast majority of computation in the brain is performed by spiking neural networks. Despite the ubiquity of such spiking, we currently lack an understanding of how biological spiking neural circuits learn and compute in vivo, as well as how we can instantiate such capabilities in artificial spiking circuits in silico. Here we revisit the problem of supervised learning in temporally coding multilayer spiking neural networks. First, by using a surrogate gradient approach, we derive SuperSpike, a nonlinear voltage-based three-factor learning rule capable of training multilayer networks of deterministic integrate-and-fire neurons to perform nonlinear computations on spatiotemporal spike patterns. Second, inspired by recent results on feedback alignment, we compare the performance of our learning rule under different credit assignment strategies for propagating output errors to hidden units. Specifically, we test uniform, symmetric, and random feedback, finding that simpler tasks can be solved with any type of feedback, while more complex tasks require symmetric feedback. In summary, our results open the door to obtaining a better scientific understanding of learning and computation in spiking neural networks by advancing our ability to train them to solve nonlinear problems involving transformations between different spatiotemporal spike time patterns. <\/jats:p>","DOI":"10.1162\/neco_a_01086","type":"journal-article","created":{"date-parts":[[2018,4,13]],"date-time":"2018-04-13T20:22:15Z","timestamp":1523650935000},"page":"1514-1541","source":"Crossref","is-referenced-by-count":480,"title":["SuperSpike: Supervised Learning in Multilayer Spiking Neural Networks"],"prefix":"10.1162","volume":"30","author":[{"given":"Friedemann","family":"Zenke","sequence":"first","affiliation":[{"name":"Department of Applied Physics, Stanford University, Stanford, CA 94305, U.S.A., and Centre for Neural Circuits and Behaviour, University of Oxford, Oxford OX1 3SR, U.K."}]},{"given":"Surya","family":"Ganguli","sequence":"additional","affiliation":[{"name":"Department of Applied Physics, Stanford University, Stanford, CA 94305, U.S.A."}]}],"member":"281","reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1038\/nn.4241"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0148948"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1038\/347069a0"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2007.12.036"},{"key":"B5","author":"Baldi P.","year":"2016","journal-title":"Learning in the machine: Random backpropagation and the learning channel"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_00829"},{"key":"B7","author":"Bengio Y.","year":"2013","journal-title":"Estimating or propagating gradients through stochastic neurons for conditional computation"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21735-7_8"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(01)00658-0"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2007.19.2.371"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipl.2005.05.023"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.4098-12.2013"},{"key":"B13","author":"Brendel W.","year":"2017","journal-title":"Learning to represent signals spike by spike"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1038\/337129a0"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_00884"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1038\/nn.4243"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2015.00099"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1126\/science.1225266"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2012.08.001"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0040233"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.6249-09.2010"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.3389\/fncir.2015.00085"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0161335"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00790"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107447615"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.28295"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1126\/science.1149639"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1111\/j.1551-6708"},{"key":"B29","author":"Guergiuev J.","year":"2016","journal-title":"Biologically feasible deep learning with segregated dendrites"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.22901"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1126\/science.aab4113"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1038\/nn1643"},{"key":"B33","author":"Hinton G.","year":"2012","journal-title":"Coursera"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhl152"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2014.00038"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2017.08.020"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms13276"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760407955"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2016.00094"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2016.00131"},{"key":"B45","first-page":"1369","volume-title":"Advances in neural information processing systems","volume":"29","author":"McIntosh L.","year":"2016"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2006.246918"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2014.03.026"},{"key":"B48","author":"Mesnard T.","year":"2016","journal-title":"Towards deep learning with spiking neurons in energy based models with contrastive Hebbian plasticity"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065712500128"},{"key":"B50","author":"Neftci E.","year":"2016","journal-title":"Neuromorphic deep learning machines"},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.1007\/BF00275687"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.3389\/fnsyn.2010.00146"},{"key":"B53","author":"Petrovici M. A.","year":"2017","journal-title":"Pattern representation and recognition with accelerated analog neuromorphic systems"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.6.1318"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2009.11-08-901"},{"key":"B56","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"B57","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.12.001"},{"key":"B58","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2016.10.011"},{"key":"B59","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00396"},{"key":"B60","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1004895"},{"key":"B61","doi-asserted-by":"publisher","DOI":"10.1038\/381520a0"},{"key":"B62","first-page":"1409","volume-title":"Advances in neural information processing systems","volume":"17","author":"Toyoizumi T.","year":"2005"},{"key":"B63","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2008.09-07-605"},{"key":"B64","doi-asserted-by":"publisher","DOI":"10.1162\/089976601300014321"},{"key":"B65","doi-asserted-by":"publisher","DOI":"10.1088\/0954-898X_8_2_003"},{"key":"B66","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"B67","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1403112111"},{"key":"B68","author":"Zenke F.","year":"2014","journal-title":"Memory formation and recall in recurrent spiking neural networks"},{"key":"B70","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms7922"},{"key":"B71","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2014.00076"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/neco_a_01086","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:42:29Z","timestamp":1615585349000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/30\/6\/1514-1541\/8378"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6]]},"references-count":67,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2018,6]]}},"alternative-id":["10.1162\/neco_a_01086"],"URL":"https:\/\/doi.org\/10.1162\/neco_a_01086","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,6]]}}}