{"id":93359,"date":"2019-07-09T11:03:18","date_gmt":"2019-07-09T18:03:18","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2019\/07\/why-artificial-neural-networks-have-a-long-way-to-go-before-they-can-see-like-us"},"modified":"2019-07-09T11:03:18","modified_gmt":"2019-07-09T18:03:18","slug":"why-artificial-neural-networks-have-a-long-way-to-go-before-they-can-see-like-us","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2019\/07\/why-artificial-neural-networks-have-a-long-way-to-go-before-they-can-see-like-us","title":{"rendered":"Why artificial neural networks have a long way to go before they can \u2018see\u2019 like us"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/why-artificial-neural-networks-have-a-long-way-to-go-before-they-can-see-like-us2.jpg\"><\/a><\/p>\n<p>Artificial neural networks were created to imitate processes in our brains, and in many respects \u2013 such as performing the quick, complex calculations necessary to win strategic games such as chess and Go \u2013 they\u2019ve already surpassed us. But if you\u2019ve ever clicked through a CAPTCHA test online to prove you\u2019re human, you know that our visual cortex still reigns supreme over its artificial imitators (for now, at least). So if schooling world chess champions has become a breeze, what\u2019s so hard about, say, positively identifying a handwritten \u20189\u2019? This explainer from the US YouTuber Grant Sanderson, who creates maths videos under the moniker 3Blue1Brown, works from a program designed to identify handwritten variations of each of the 10 Arabic numerals (0\u22129) to detail the basics of how artificial neural networks operate. It\u2019s a handy crash-course \u2013 and one that will almost certainly make you appreciate the extraordinary amount of work your brain does to accomplish what might seem like simple tasks.<\/p>\n<p>Video by <a href=\"http:\/\/www.3blue1brown.com\" rel=\"\">3Blue1Brown<\/a><\/p>\n<p>The work of a sleepwalking artist offers a glimpse into the fertile slumbering brain.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Artificial neural networks were created to imitate processes in our brains, and in many respects \u2013 such as performing the quick, complex calculations necessary to win strategic games such as chess and Go \u2013 they\u2019ve already surpassed us. But if you\u2019ve ever clicked through a CAPTCHA test online to prove you\u2019re human, you know that [\u2026]<\/p>\n","protected":false},"author":511,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1509,6],"tags":[],"class_list":["post-93359","post","type-post","status-publish","format-standard","hentry","category-entertainment","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/93359","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/511"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=93359"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/93359\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=93359"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=93359"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=93359"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}