{"id":173769,"date":"2023-10-08T12:31:24","date_gmt":"2023-10-08T17:31:24","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2023\/10\/meta-learning-machines-in-a-single-lifelong-trial"},"modified":"2023-10-08T12:31:24","modified_gmt":"2023-10-08T17:31:24","slug":"meta-learning-machines-in-a-single-lifelong-trial","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2023\/10\/meta-learning-machines-in-a-single-lifelong-trial","title":{"rendered":"Meta-Learning Machines in a Single Lifelong Trial"},"content":{"rendered":"<p><\/p>\n<p><iframe loading=\"lazy\" title=\"Meta-Learning Machines in a Single Lifelong Trial\" width=\"640\" height=\"360\" src=\"https:\/\/www.youtube.com\/embed\/2GgGVdkq2bU?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe><\/p>\n<p>The most widely used machine learning algorithms were designed by humans and thus are hindered by our cognitive biases and limitations. Can we also construct meta-learning algorithms that can learn better learning algorithms so that our self-improving AIs have no limits other than those inherited from computability and physics? This question has been a main driver of my research since I wrote a thesis on it in 1987. In the past decade, it has become a driver of many other people\u2019s research as well. Here I summarize our work starting in 1994 on meta-reinforcement learning with self-modifying policies in a single lifelong trial, and \u2014 since 2003 \u2014 mathematically optimal meta-learning through the self-referential G\u00f6del Machine. This talk was previously presented at meta-learning workshops at ICML 2020 and NeurIPS 2021. Many additional publications on meta-learning can be found at <a href=\"https:\/\/people.idsia.ch\/~juergen\/metalearning.html\">https:\/\/people.idsia.ch\/~juergen\/metalearning.html<\/a>.<\/p>\n<p>J\u00fcrgen Schmidhuber.<br \/> Director, AI Initiative, KAUST<br \/> Scientific Director of the Swiss AI Lab IDSIA<br \/> Co-Founder &amp; Chief Scientist, NNAISENSE<br \/>\n<a href=\"http:\/\/www.idsia.ch\/~juergen\/blog.html\">http:\/\/www.idsia.ch\/~juergen\/blog.html<\/a>.<\/p>\n<p><a class=\"twitter-timeline\" data-width=\"640\" data-height=\"960\" data-dnt=\"true\" href=\"https:\/\/twitter.com\/SchmidhuberAI?ref_src=twsrc%5Etfw\"><br \/> Tweets by SchmidhuberAI<\/a><script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n","protected":false},"excerpt":{"rendered":"<p>The most widely used machine learning algorithms were designed by humans and thus are hindered by our cognitive biases and limitations. Can we also construct meta-learning algorithms that can learn better learning algorithms so that our self-improving AIs have no limits other than those inherited from computability and physics? This question has been a main [\u2026]<\/p>\n","protected":false},"author":661,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[41,219,6],"tags":[],"class_list":["post-173769","post","type-post","status-publish","format-standard","hentry","category-information-science","category-physics","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/173769","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\/661"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=173769"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/173769\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=173769"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=173769"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=173769"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}