{"id":11707,"date":"2020-09-24T07:58:21","date_gmt":"2020-09-24T11:58:21","guid":{"rendered":"http:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/?p=11707"},"modified":"2020-09-24T07:58:21","modified_gmt":"2020-09-24T11:58:21","slug":"looking-inside-the-blackbox-how-to-trick-a-neural-network","status":"publish","type":"post","link":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/looking-inside-the-blackbox-how-to-trick-a-neural-network\/11707\/","title":{"rendered":"Looking Inside The Blackbox \u2014 How To Trick A Neural Network"},"content":{"rendered":"Neural networks get a bad reputation for being black boxes. And while it certainly takes creativity to understand their decision making, they are really not as opaque as people would have you believe. In this tutorial, I\u2019ll show you how to use backpropagation to change the input as to classify it as whatever you would like. Follow along using this colab. Humans as black boxes Let\u2019s consider the case of humans. If I show you the following input: there\u2019s a good chance you have no idea whether this is a 5 or a 6. In fact, I believe <a href=\"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/looking-inside-the-blackbox-how-to-trick-a-neural-network\/11707\/\" class=\"more-link\">(more&hellip;)<\/a>","protected":false},"excerpt":{"rendered":"<p>Neural networks get a bad reputation for being black boxes. And while it certainly takes creativity to understand their decision making, they are really not as opaque as people would have you believe. In this tutorial, I\u2019ll show you how to use backpropagation to change the input as to classify it as whatever you would [&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":[59,1130,243,1074,1119],"class_list":["post-11707","post","type-post","status-publish","format-standard","hentry","category-industry-news","category-left-hand","tag-analytics","tag-blackbox","tag-machine-learning","tag-machine-learning-analytics","tag-neural-networks"],"_links":{"self":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/11707","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=11707"}],"version-history":[{"count":1,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/11707\/revisions"}],"predecessor-version":[{"id":11711,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/11707\/revisions\/11711"}],"wp:attachment":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/media?parent=11707"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/categories?post=11707"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/tags?post=11707"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}