<\/p>\n
<\/iframe><\/p>\n<p>We\u2019re in a golden age of merging AI and neuroscience. No longer tied to conventional publication venues with year-long turnaround times, our field is moving at record speed. As 2021 draws to a close, I wanted to take some time to zoom out and review a recent trend in neuro-AI, the move toward unsupervised learning to explain representations in different brain areas<sup>footnote<\/sup>.<\/p>\n<p>One of the most robust findings in neuro-AI is that artificial neural networks trained to perform ecologically relevant tasks match single neurons and ensemble signals in the brain. The canonical example is the ventral stream, where <a href=\"https:\/\/openreview.net\/forum?id=i_xiyGq6FNT\">DNNs trained for object recognition on ImageNet match representations in IT<\/a> (Khaligh-Razavi & Kriegeskorte, 2014, Yamins et al. 2014). Supervised, task-optimized networks link two important forms of explanation: ecological relevance and accounting for neural activity. They answer the teleological question: what is a brain region for?<\/p>\n<p>However, as Jess Thompson points out, these are far from the only forms of explanation. In particular, task-optimized networks are generally not considered biologically plausible. Conventional ImageNet training uses 1M images. For a human infant to get this level of supervision, they would have to receive a new supervised label every 5 seconds (e.g. the parent points at a duck and says \u201cduck\u201d) for 3 hours a day, for more than a year. And for a non-human primate or a mouse? Thus, the search for biologically plausible networks which match the human brain is still on.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We\u2019re in a golden age of merging AI and neuroscience. No longer tied to conventional publication venues with year-long turnaround times, our field is moving at record speed. As 2021 draws to a close, I wanted to take some time to zoom out and review a recent trend in neuro-AI, the move toward unsupervised learning [\u2026]<\/p>\n","protected":false},"author":556,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[47,6],"tags":[],"class_list":["post-133466","post","type-post","status-publish","format-standard","hentry","category-neuroscience","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/133466","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\/556"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=133466"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/133466\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=133466"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=133466"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=133466"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}