{"id":12160,"date":"2021-06-07T08:34:05","date_gmt":"2021-06-07T12:34:05","guid":{"rendered":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/?p=12160"},"modified":"2021-06-07T08:34:05","modified_gmt":"2021-06-07T12:34:05","slug":"do-wide-and-deep-networks-learn-the-same-things","status":"publish","type":"post","link":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/do-wide-and-deep-networks-learn-the-same-things\/12160\/","title":{"rendered":"Do Wide and Deep Networks Learn the Same Things?"},"content":{"rendered":"Originally published in Google AI Blog, May 4, 2021. A common practice to improve a neural network\u2019s performance and tailor it to available computational resources is to\u00a0adjust the architecture depth and width. Indeed, popular families of neural networks,\u00a0 including\u00a0 EfficientNet,\u00a0ResNet\u00a0and\u00a0Transformers, consist of a set of architectures of flexible depths and widths. However, beyond the effect on accuracy, there is limited understanding of how these fundamental choices of architecture design affect the model, such as the impact on its internal representations. In \u201cDo Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width <a href=\"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/do-wide-and-deep-networks-learn-the-same-things\/12160\/\" class=\"more-link\">(more&hellip;)<\/a>","protected":false},"excerpt":{"rendered":"<p>Originally published in Google AI Blog, May 4, 2021. A common practice to improve a neural network\u2019s performance and tailor it to available computational resources is to\u00a0adjust the architecture depth and width. Indeed, popular families of neural networks,\u00a0 including\u00a0 EfficientNet,\u00a0ResNet\u00a0and\u00a0Transformers, consist of a set of architectures of flexible depths and widths. However, beyond the effect [&hellip;]<\/p>\n","protected":false},"author":72,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","_links_to":"","_links_to_target":""},"categories":[11,48],"tags":[879,59,368,230,243,1175],"class_list":["post-12160","post","type-post","status-publish","format-standard","hentry","category-industry-news","category-left-hand","tag-ai","tag-analytics","tag-artificial-intelligence","tag-data-analytics","tag-machine-learning","tag-machine-learning-data"],"_links":{"self":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/12160","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/users\/72"}],"replies":[{"embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/comments?post=12160"}],"version-history":[{"count":2,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/12160\/revisions"}],"predecessor-version":[{"id":12162,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/12160\/revisions\/12162"}],"wp:attachment":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/media?parent=12160"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/categories?post=12160"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/tags?post=12160"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}