{"id":129246,"date":"2021-10-20T02:24:51","date_gmt":"2021-10-20T09:24:51","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2021\/10\/neuron-bursts-can-mimic-famous-ai-learning-strategy"},"modified":"2021-10-20T02:24:51","modified_gmt":"2021-10-20T09:24:51","slug":"neuron-bursts-can-mimic-famous-ai-learning-strategy","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2021\/10\/neuron-bursts-can-mimic-famous-ai-learning-strategy","title":{"rendered":"Neuron Bursts Can Mimic Famous AI Learning Strategy"},"content":{"rendered":"

<\/a><\/p>\n

Every time a human or machine learns how to get better at a task, a trail of evidence is left behind. A sequence of physical changes \u2014 to cells in a brain or to numerical values in an algorithm \u2014 underlie the improved performance. But how the system figures out exactly what changes to make is no small feat. It\u2019s called the credit assignment problem, in which a brain or artificial intelligence system must pinpoint which pieces in its pipeline are responsible for errors and then make the necessary changes. Put more simply: It\u2019s a blame game to find who\u2019s at fault.<\/p>\n

AI engineers solved the credit assignment problem for machines with a powerful algorithm called backpropagation, popularized in 1986 with the work<\/a> of Geoffrey Hinton, David Rumelhart and Ronald Williams. It\u2019s now the workhorse that powers learning in the most successful AI systems, known as deep neural networks, which have hidden layers of artificial \u201cneurons\u201d between their input and output layers. And now, in a paper<\/a> published in Nature Neuroscience<\/em> in May, scientists may finally have found an equivalent for living brains that could work in real time.<\/p>\n

A team of researchers led by Richard Naud<\/a> of the University of Ottawa and Blake Richards<\/a> of McGill University and the Mila AI Institute in Quebec revealed a new model of the brain\u2019s learning algorithm that can mimic the backpropagation process. It appears so realistic that experimental neuroscientists have taken notice and are now interested in studying real neurons to find out whether the brain is actually doing it.<\/p>\n","protected":false},"excerpt":{"rendered":"

Every time a human or machine learns how to get better at a task, a trail of evidence is left behind. A sequence of physical changes \u2014 to cells in a brain or to numerical values in an algorithm \u2014 underlie the improved performance. But how the system figures out exactly what changes to make [\u2026]<\/p>\n","protected":false},"author":396,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[41,6],"tags":[],"class_list":["post-129246","post","type-post","status-publish","format-standard","hentry","category-information-science","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/129246","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/396"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=129246"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/129246\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=129246"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=129246"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=129246"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}