{"id":674591,"date":"2020-12-01T15:40:41","date_gmt":"2020-12-01T19:40:41","guid":{"rendered":"http:\/\/spaceweekly.com\/?p=674591"},"modified":"2020-12-01T15:40:41","modified_gmt":"2020-12-01T19:40:41","slug":"shrinking-massive-neural-networks-used-to-model-language","status":"publish","type":"post","link":"https:\/\/spaceweekly.com\/?p=674591","title":{"rendered":"Shrinking massive neural networks used to model language"},"content":{"rendered":"<p>Deep learning neural networks can be massive, demanding major computing power. In a test of the &#8216;lottery ticket hypothesis,&#8217; researchers have found leaner, more efficient subnetworks hidden within BERT models. The discovery could make natural language processing more accessible.&#013;<br \/>\n&#013;<br \/>\n&#013;<br \/>\n Click here for original story, <a href=\"https:\/\/www.sciencedaily.com\/releases\/2020\/12\/201201144041.htm\" target=\"_blank\" rel=\"nofollow noopener noreferrer\">Shrinking massive neural networks used to model language<\/a>&#013;<br \/>\n&#013;<br \/>\n&#013;<br \/>\nSource: ScienceDaily&#013;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Deep learning neural networks can be massive, demanding major computing power. In a test of the &#8216;lottery ticket hypothesis,&#8217; researchers have found leaner, more efficient subnetworks hidden within BERT models.&hellip; <\/p>\n","protected":false},"author":1,"featured_media":615444,"comment_status":"false","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[13],"tags":[],"class_list":["post-674591","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-genaero"],"_links":{"self":[{"href":"https:\/\/spaceweekly.com\/index.php?rest_route=\/wp\/v2\/posts\/674591","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/spaceweekly.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/spaceweekly.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/spaceweekly.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/spaceweekly.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=674591"}],"version-history":[{"count":0,"href":"https:\/\/spaceweekly.com\/index.php?rest_route=\/wp\/v2\/posts\/674591\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/spaceweekly.com\/index.php?rest_route=\/wp\/v2\/media\/615444"}],"wp:attachment":[{"href":"https:\/\/spaceweekly.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=674591"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/spaceweekly.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=674591"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/spaceweekly.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=674591"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}