{"id":49,"date":"2020-08-12T10:26:31","date_gmt":"2020-08-12T14:26:31","guid":{"rendered":"https:\/\/www.macloo.com\/ai\/?p=49"},"modified":"2020-08-24T12:07:12","modified_gmt":"2020-08-24T16:07:12","slug":"ask-a-computer-to-draw-what-it-sees","status":"publish","type":"post","link":"https:\/\/www.macloo.com\/ai\/2020\/08\/12\/ask-a-computer-to-draw-what-it-sees\/","title":{"rendered":"Ask a computer to draw what it sees"},"content":{"rendered":"\n<p>If a computer can correctly <em>identify<\/em> an object (an apple, a tricycle) or an animal such as a zebra, can it produce a <em>drawing<\/em> of that object or animal? This is something most people can do, even if their drawing skills are minimal. After all, almost anyone can play Pictionary.<\/p>\n\n\n\n<p>This 8-minute video shows us what happened when a programmer-artist reversed the process of an AI that recognizes objects and animals in digital images. I really admire the deft storytelling here.<\/p>\n\n\n\n<figure class=\"wp-block-embed-youtube aligncenter wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<div class=\"jetpack-video-wrapper\"><iframe loading=\"lazy\" title=\"What the world looks like to an algorithm\" width=\"739\" height=\"416\" src=\"https:\/\/www.youtube.com\/embed\/PwcuTCfSIyI?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen><\/iframe><\/div>\n<\/div><\/figure>\n\n\n\n<p>Object recognition has improved amazingly in the past 10 years, but that does not mean these AI systems <em>see<\/em> the same way as a human does. In some cases, that might not matter at all. In other cases, it can mean the difference <a rel=\"noreferrer noopener\" href=\"https:\/\/electrek.co\/2016\/07\/01\/understanding-fatal-tesla-accident-autopilot-nhtsa-probe\/\" target=\"_blank\">between life and death<\/a>.<\/p>\n\n\n\n<p>In <a href=\"https:\/\/www.macloo.com\/ai\/2020\/08\/11\/how-machines-see\/\">yesterday&#8217;s post<\/a> I mentioned the way a convolutional neural network (part of a machine learning system) processes an image through many stacked <em>layers<\/em> of detection units (sometimes called <em>neurons<\/em>), identifying edges and shapes that eventually lead to a conclusion that the image is likely to contain such-and-such an object, animal, or person. Today&#8217;s video shows a bit more about the <em>training process<\/em> that an AI goes through before it can perform these identifications.<\/p>\n\n\n\n<p>Training is necessary in the type of machine learning called <strong>supervised learning<\/strong>. The <em>training dat<\/em>a (in this case, digital images of objects and animals) must be labeled in advance. That is, the system receives thousands of images <em>labeled &#8220;tiger&#8221;<\/em> before it is able to recognize a tiger in a random photo or video. If a system can identify 20 different animals, that system was trained on thousands of images of <em>each<\/em> animal.<\/p>\n\n\n\n<p>If the system was never trained on tigers, it cannot recognize a tiger.<\/p>\n\n\n\n<p>So today&#8217;s video gives us a nice glimpse into how and why that training works, and what its limitations are. What&#8217;s really fascinating to me, though, are the images produced by programmer-artist <a rel=\"noreferrer noopener\" href=\"https:\/\/aiartists.org\/tom-white\" target=\"_blank\">Tom White<\/a>&#8216;s system. <\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\"><p>&#8220;I have created a drawing system that allows neural networks to produce abstract ink prints that reveal their visual concepts. Surprisingly, these prints are recognized not only by the neural networks that created them, but also universally across most AI systems which have been trained to recognize the same objects.&#8221;<\/p><cite>\u2014Tom White<\/cite><\/blockquote>\n\n\n\n<p>In the video, you&#8217;ll see that <em>humans cannot recognize what the AI drew<\/em>. The rendering is too abstract, too <em>unlike<\/em> what we see and what we would draw ourselves. Note what White says, though, about other AI systems: they <em>can<\/em> recognize the object in these AI-produced drawings.<\/p>\n\n\n\n<p>This is, I think, related to what is called <em>adversarial AI, <\/em>which I&#8217;ll discuss in a future post.<\/p>\n\n\n\n<p><a rel=\"license\" href=\"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/\"><img decoding=\"async\" alt=\"Creative Commons License\" style=\"border-width:0\" src=\"https:\/\/i.creativecommons.org\/l\/by-nc-nd\/4.0\/88x31.png\"><\/a><br>\n<small><span xmlns:dct=\"http:\/\/purl.org\/dc\/terms\/\" property=\"dct:title\"><strong>AI in Media and Society<\/strong><\/span> by <span xmlns:cc=\"http:\/\/creativecommons.org\/ns#\" property=\"cc:attributionName\">Mindy McAdams<\/span> is licensed under a <a rel=\"license\" href=\"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/\">Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License<\/a>.<br>\nInclude the author&#8217;s name (Mindy McAdams) and a link to the original post in any reuse of this content.<\/small><\/p>\n\n\n\n<p>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>If a computer can correctly identify an object (an apple, a tricycle) or an animal such as a zebra, can it produce a drawing of that object or animal? This is something most people can do, even if their drawing skills are minimal. After all, almost anyone can play Pictionary. This 8-minute video shows us&hellip; <a class=\"more-link\" href=\"https:\/\/www.macloo.com\/ai\/2020\/08\/12\/ask-a-computer-to-draw-what-it-sees\/\">Continue reading <span class=\"screen-reader-text\">Ask a computer to draw what it sees<\/span> <span class=\"meta-nav\" aria-hidden=\"true\">&rarr;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[3,5],"tags":[20,16,17,19,18],"class_list":["post-49","post","type-post","status-publish","format-standard","hentry","category-image-recognition","category-machine-learning","tag-art","tag-drawing","tag-perception","tag-supervised_learning","tag-training"],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/www.macloo.com\/ai\/wp-json\/wp\/v2\/posts\/49","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.macloo.com\/ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.macloo.com\/ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.macloo.com\/ai\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.macloo.com\/ai\/wp-json\/wp\/v2\/comments?post=49"}],"version-history":[{"count":4,"href":"https:\/\/www.macloo.com\/ai\/wp-json\/wp\/v2\/posts\/49\/revisions"}],"predecessor-version":[{"id":194,"href":"https:\/\/www.macloo.com\/ai\/wp-json\/wp\/v2\/posts\/49\/revisions\/194"}],"wp:attachment":[{"href":"https:\/\/www.macloo.com\/ai\/wp-json\/wp\/v2\/media?parent=49"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.macloo.com\/ai\/wp-json\/wp\/v2\/categories?post=49"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.macloo.com\/ai\/wp-json\/wp\/v2\/tags?post=49"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}