{"id":619,"date":"2022-01-21T10:38:24","date_gmt":"2022-01-21T10:38:24","guid":{"rendered":"https:\/\/wellai.health\/blog\/?p=619"},"modified":"2022-01-21T10:38:24","modified_gmt":"2022-01-21T10:38:24","slug":"the-comeback-of-convolutional-nets","status":"publish","type":"post","link":"https:\/\/wellai.health\/blog\/the-comeback-of-convolutional-nets\/","title":{"rendered":"The Comeback of Convolutional Nets"},"content":{"rendered":"<p><strong>The eternal fight between ConvNets and Transformers continues.\u00a0 Well, an eternity in machine learning is about 5 years. <\/strong><strong>\ud83d\ude0a<\/strong><\/p>\n<p>&nbsp;<\/p>\n<p>The Facebook AI researchers published a nice paper a few days ago titled \u201cA ConvNet for the 2020s\u201d:<\/p>\n<p><a href=\"https:\/\/arxiv.org\/pdf\/2201.03545.pdf\">https:\/\/arxiv.org\/pdf\/2201.03545.pdf<\/a><\/p>\n<p>&nbsp;<\/p>\n<p>What we gathered from this study is what we have been preaching all along: if you are a data scientist, don\u2019t throw yourself into days and weeks of testing the most \u201crecommended\u201d algorithm out there.\u00a0 Evaluate the problem.\u00a0 Think what the best and the most effective way to solve the problem.\u00a0 Throwing \u201cthe latest and the greatest\u201d at the problem may impress your boss.\u00a0 And that\u2019s OK.\u00a0 But be humble.\u00a0 Sometimes a least squares regression could be the best solution.<\/p>\n<p>&nbsp;<\/p>\n<p>In this Facebook AI study, the authors are challenging the argument that in computer vision, Vision Transformers (ViTs) have been superior to ConvNets in image classification and recognition.\u00a0 As the world moves to super high definition images right on your iPhone, Transformers have become computationally expensive and also started to lose in modeling complexity to some of the latest ConvNets algorithms.\u00a0 The hybrid approach sometimes works best.<\/p>\n<p><strong>\u00a0<\/strong><\/p>\n<p><strong>In our ongoing educational series, Daniel Satchkov, head of machine learning at WellAI, briefly talks about the beauty and the elegance of Convolutional Nets and their applications in dermatology and radiology, and also explains \u00a0how cats see the world. <\/strong><strong>\ud83d\ude0a<\/strong><\/p>\n<p>&nbsp;<\/p>\n<p><iframe loading=\"lazy\" title=\"Convolutional Neural Networks (CNN) - applications in image recognition in dermatology and radiology\" width=\"800\" height=\"450\" src=\"https:\/\/www.youtube.com\/embed\/p3fWD-z_X-Y?feature=oembed&#038;enablejsapi=1&#038;origin=https:\/\/wellai.health\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen><\/iframe><\/p>\n<p>&nbsp;<\/p>\n<p>We are at the very beginning of understanding applications of mathematics and data science in medicine and other fields of life!<\/p>\n<p>&nbsp;<\/p>\n<p>Stay healthy!\u00a0 Stay knowledgeable about your health.<\/p>\n<p>&nbsp;<\/p>\n<p>Happy and Healthy 2022!<\/p>\n<p>WellAI Team<\/p>\n<p><a href=\"https:\/\/wellai.health\">wellai.health<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>The eternal fight between ConvNets and Transformers continues.\u00a0 Well, an eternity in machine learning is about 5 years.<\/p>\n","protected":false},"author":3,"featured_media":620,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"video","meta":[],"categories":[175,179],"tags":[194,193,6,192],"jetpack_featured_media_url":"https:\/\/i0.wp.com\/wellai.health\/blog\/wp-content\/uploads\/2022\/01\/The-Comeback-of-Convolutional-Nets-e1642761464301.jpg?fit=700%2C392&ssl=1","jetpack_sharing_enabled":true,"jetpack_likes_enabled":true,"_links":{"self":[{"href":"https:\/\/wellai.health\/blog\/wp-json\/wp\/v2\/posts\/619"}],"collection":[{"href":"https:\/\/wellai.health\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wellai.health\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wellai.health\/blog\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/wellai.health\/blog\/wp-json\/wp\/v2\/comments?post=619"}],"version-history":[{"count":1,"href":"https:\/\/wellai.health\/blog\/wp-json\/wp\/v2\/posts\/619\/revisions"}],"predecessor-version":[{"id":621,"href":"https:\/\/wellai.health\/blog\/wp-json\/wp\/v2\/posts\/619\/revisions\/621"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/wellai.health\/blog\/wp-json\/wp\/v2\/media\/620"}],"wp:attachment":[{"href":"https:\/\/wellai.health\/blog\/wp-json\/wp\/v2\/media?parent=619"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wellai.health\/blog\/wp-json\/wp\/v2\/categories?post=619"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wellai.health\/blog\/wp-json\/wp\/v2\/tags?post=619"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}