{"id":11950,"date":"2021-02-13T11:10:40","date_gmt":"2021-02-13T16:10:40","guid":{"rendered":"http:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/?p=11950"},"modified":"2021-02-13T11:10:40","modified_gmt":"2021-02-13T16:10:40","slug":"gradient-descent-models-are-kernel-machines-deep-learning","status":"publish","type":"post","link":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/gradient-descent-models-are-kernel-machines-deep-learning\/11950\/","title":{"rendered":"Gradient Descent Models Are Kernel Machines (Deep Learning)"},"content":{"rendered":"Originally published in infoproc.blogspot.com, Feb 7, 2021. This paper shows that models which result from gradient descent training (e.g., deep neural nets) can be expressed as a weighted sum of similarity functions (kernels) which measure the similarity of a given instance to the examples used in training. The kernels are defined by the inner product of model gradients in the parameter space, integrated over the descent (learning) path. Roughly speaking, two data points x and x&#8217; are similar, i.e., have large kernel function K(x,x&#8217;), if they have similar effects on the model parameters in the gradient descent. With <a href=\"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/gradient-descent-models-are-kernel-machines-deep-learning\/11950\/\" class=\"more-link\">(more&hellip;)<\/a>","protected":false},"excerpt":{"rendered":"<p>Originally published in infoproc.blogspot.com, Feb 7, 2021. This paper shows that models which result from gradient descent training (e.g., deep neural nets) can be expressed as a weighted sum of similarity functions (kernels) which measure the similarity of a given instance to the examples used in training. The kernels are defined by the inner product [&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":[59,368,791,1160,243],"class_list":["post-11950","post","type-post","status-publish","format-standard","hentry","category-industry-news","category-left-hand","tag-analytics","tag-artificial-intelligence","tag-deep-learning","tag-kernal-function","tag-machine-learning"],"_links":{"self":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/11950","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=11950"}],"version-history":[{"count":16,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/11950\/revisions"}],"predecessor-version":[{"id":11966,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/11950\/revisions\/11966"}],"wp:attachment":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/media?parent=11950"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/categories?post=11950"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/tags?post=11950"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}