{"id":76101,"date":"2018-02-20T05:44:01","date_gmt":"2018-02-20T13:44:01","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2018\/02\/deepminds-latest-ai-transfers-its-learning-to-new-tasks"},"modified":"2018-02-25T11:14:21","modified_gmt":"2018-02-25T19:14:21","slug":"deepminds-latest-ai-transfers-its-learning-to-new-tasks","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2018\/02\/deepminds-latest-ai-transfers-its-learning-to-new-tasks","title":{"rendered":"DeepMind\u2019s latest AI transfers its learning to new tasks"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/deepminds-latest-ai-transfers-its-learning-to-new-tasks.gif\"><\/a><\/p>\n<p>By using insights from one job to help it do another, a successful new artificial intelligence hints at a more versatile future for machine learning.<\/p>\n<p><strong>Backstory:<\/strong> Most algorithms can be trained in only one domain, and can\u2019t use what\u2019s been learned for one task to perform another, new one. A big hope for AI is to have systems take insights from one setting and apply them elsewhere\u2014what\u2019s called transfer learning.<\/p>\n<p><strong>What\u2019s new:<\/strong> DeepMind built a new AI system called <a href=\"https:\/\/arxiv.org\/abs\/1802.01561\">IMPALA<\/a> that simultaneously performs multiple tasks\u2014in this case, playing 57 Atari games\u2014and attempts to share learning between them. It showed signs of transferring what was learned from one game to another.<\/p>\n<p><!-- Link: <a href=\"https:\/\/www.technologyreview.com\/the-download\/610244\/deepminds-latest-ai-transfers-its-learning-to-new-tasks\/\">https:\/\/www.technologyreview.com\/the-download\/610244\/deepmin...new-tasks\/<\/a> --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>By using insights from one job to help it do another, a successful new artificial intelligence hints at a more versatile future for machine learning. Backstory: Most algorithms can be trained in only one domain, and can\u2019t use what\u2019s been learned for one task to perform another, new one. A big hope for AI is [\u2026]<\/p>\n","protected":false},"author":367,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[41,6],"tags":[],"class_list":["post-76101","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\/76101","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\/367"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=76101"}],"version-history":[{"count":1,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/76101\/revisions"}],"predecessor-version":[{"id":76202,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/76101\/revisions\/76202"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=76101"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=76101"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=76101"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}