{"id":15266,"date":"2019-11-05T09:34:17","date_gmt":"2019-11-05T09:34:17","guid":{"rendered":"https:\/\/www.icebreakerexecutive.com\/?p=15266"},"modified":"2019-11-05T09:34:17","modified_gmt":"2019-11-05T09:34:17","slug":"gan-networks-deep-fakes","status":"publish","type":"post","link":"https:\/\/winningthinking.co.uk\/?p=15266","title":{"rendered":"GAN networks &#8211; deep fakes"},"content":{"rendered":"<div class=\"video-shortcode\"><iframe title=\"Everybody Dance Now\" width=\"1778\" height=\"1000\" src=\"https:\/\/www.youtube.com\/embed\/PCBTZh41Ris?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe><\/div>\n<p id=\"97a4\" class=\"hq hr du bh hs b ht hu hv hw hx hy hz ia ib ic id\" data-selectable-paragraph=\"\">&#8220;Their secret lies in the way two neural networks work together \u2014 or rather, against each other. You start by feeding both neural networks a whole lot of training data and give each one a separate task. The first network, known as the generator, must produce artificial outputs, like handwriting, videos, or voices, by looking at the training examples and trying to mimic them. The second, known as the discriminator, then determines whether the outputs are real by comparing each one with the same training examples.<\/p>\n<p id=\"27a5\" class=\"hq hr du bh hs b ht hu hv hw hx hy hz ia ib ic id\" data-selectable-paragraph=\"\">Each time the discriminator successfully rejects the generator\u2019s output, the generator goes back to try again. To borrow a\u00a0<a class=\"cc gp ii ij ik il\" href=\"https:\/\/www.technologyreview.com\/s\/610253\/the-ganfather-the-man-whos-given-machines-the-gift-of-imagination\/\" target=\"_blank\" rel=\"noopener nofollow noreferrer\">metaphor<\/a>\u00a0from my colleague Martin Giles, the process \u201cmimics the back-and-forth between a picture forger and an art detective who repeatedly try to outwit one another.\u201d Eventually, the discriminator can\u2019t tell the difference between the output and training examples.\u00a0<mark class=\"oa ob jt\">In other words, the mimicry is indistinguishable from reality.&#8221;<\/mark><\/p>\n<p data-selectable-paragraph=\"\">quoted credit Medium<\/p>\n","protected":false},"excerpt":{"rendered":"<p>&#8220;Their secret lies in the way two neural networks work  [&#8230;]<\/p>\n","protected":false},"author":5,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-15266","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/winningthinking.co.uk\/index.php?rest_route=\/wp\/v2\/posts\/15266","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/winningthinking.co.uk\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/winningthinking.co.uk\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/winningthinking.co.uk\/index.php?rest_route=\/wp\/v2\/users\/5"}],"replies":[{"embeddable":true,"href":"https:\/\/winningthinking.co.uk\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=15266"}],"version-history":[{"count":0,"href":"https:\/\/winningthinking.co.uk\/index.php?rest_route=\/wp\/v2\/posts\/15266\/revisions"}],"wp:attachment":[{"href":"https:\/\/winningthinking.co.uk\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=15266"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/winningthinking.co.uk\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=15266"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/winningthinking.co.uk\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=15266"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}