{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T01:40:21Z","timestamp":1718070021700},"reference-count":12,"publisher":"MIT Press","issue":"7","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>In recent years, there has been an intense debate about how learning in biological neural networks (BNNs) differs from learning in artificial neural networks. It is often argued that the updating of connections in the brain relies only on local information, and therefore a stochastic gradient-descent type optimization method cannot be used. In this note, we study a stochastic model for supervised learning in BNNs. We show that a (continuous) gradient step occurs approximately when each learning opportunity is processed by many local updates. This result suggests that stochastic gradient descent may indeed play a role in optimizing BNNs.<\/jats:p>","DOI":"10.1162\/neco_a_01668","type":"journal-article","created":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T21:20:02Z","timestamp":1714166402000},"page":"1424-1432","update-policy":"http:\/\/dx.doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":0,"title":["Is Learning in Biological Neural Networks Based on Stochastic Gradient Descent? An Analysis Using Stochastic Processes"],"prefix":"10.1162","volume":"36","author":[{"given":"S\u00f6ren","family":"Christensen","sequence":"first","affiliation":[{"name":"Department of Mathematics, Kiel Universiy, 24118 Kiel, Germany christensen@math.uni-kiel.de"}]},{"given":"Jan","family":"Kallsen","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Kiel Universiy, 24118 Kiel, Germany kallsen@math.uni-kiel.de"}]}],"member":"281","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"2024061101141096300_bib1","doi-asserted-by":"crossref","DOI":"10.1137\/1.9780898718768","volume-title":"Introduction to derivative-free optimization","author":"Conn","year":"2009"},{"issue":"6203","key":"2024061101141096300_bib2","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1038\/337129a0","article-title":"The recent excitement about neural networks","volume":"37","author":"Crick","year":"1989","journal-title":"Nature"},{"issue":"5","key":"2024061101141096300_bib3","doi-asserted-by":"publisher","first-page":"2788","DOI":"10.1109\/TIT.2015.2409256","article-title":"Optimal rates for zero-order convex optimization: The power of two function evaluations","volume":"61","author":"Duchi","year":"2015","journal-title":"IEEE Transactions on Information Theory"},{"issue":"1","key":"2024061101141096300_bib4","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1111\/j.1551-6708.1987.tb00862.x","article-title":"Competitive learning: From interactive activation to adaptive resonance","volume":"11","author":"Grossberg","year":"1987","journal-title":"Cognitive Science"},{"key":"2024061101141096300_bib5","doi-asserted-by":"crossref","DOI":"10.4324\/9781410612403","volume-title":"The organization of behavior: A neuropsychological theory","author":"Hebb","year":"2005"},{"issue":"6","key":"2024061101141096300_bib6","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1038\/s41583-020-0277-3","article-title":"Backpropagation and the brain","volume":"21","author":"Lillicrap","year":"2020","journal-title":"Nature Reviews Neuroscience"},{"issue":"47","key":"2024061101141096300_bib7","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2105395118","article-title":"Single-neuron firing cascades underlie global spontaneous brain events","volume":"118","author":"Liu","year":"2021","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"2024061101141096300_bib8","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1007\/s10208-015-9296-2","article-title":"Random gradient-free minimization of convex functions","volume":"17","author":"Nesterov","year":"2017","journal-title":"Foundations of Computational Mathematics"},{"key":"2024061101141096300_bib9","article-title":"Shadowing properties of optimization algorithms","volume-title":"Advances in neural information processing systems","author":"Orvieto","year":"2019"},{"key":"2024061101141096300_bib10","author":"Schmidt-Hieber","year":"2023","journal-title":"Interpreting learning in biological neural networks as zero-order optimization method"},{"key":"2024061101141096300_bib11","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":"2019","journal-title":"Neural Networks"},{"issue":"3","key":"2024061101141096300_bib12","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1016\/j.tics.2018.12.005","article-title":"Theories of error back-propagation in the brain","volume":"23","author":"Whittington","year":"2019","journal-title":"Trends in Cognitive Sciences"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/36\/7\/1424\/2378040\/neco_a_01668.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/36\/7\/1424\/2378040\/neco_a_01668.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T01:14:21Z","timestamp":1718068461000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/36\/7\/1424\/120663\/Is-Learning-in-Biological-Neural-Networks-Based-on"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,7]]},"references-count":12,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2024,6,7]]},"published-print":{"date-parts":[[2024,6,7]]}},"URL":"https:\/\/doi.org\/10.1162\/neco_a_01668","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,7]]},"published":{"date-parts":[[2024,6,7]]}}}