{"id":22309,"date":"2016-02-18T12:48:41","date_gmt":"2016-02-18T20:48:41","guid":{"rendered":"http:\/\/lifeboat.com\/blog\/2016\/02\/brain-scan-for-artificial-intelligence-shows-how-software-thinks"},"modified":"2017-04-24T22:17:46","modified_gmt":"2017-04-25T05:17:46","slug":"brain-scan-for-artificial-intelligence-shows-how-software-thinks","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2016\/02\/brain-scan-for-artificial-intelligence-shows-how-software-thinks","title":{"rendered":"Brain scan for artificial intelligence shows how software thinks"},"content":{"rendered":"<p><a class=\"blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/brain-scan-for-artificial-intelligence-shows-how-software-thinks.jpg\"><\/a><\/p>\n<p>Neural networks have become enormously successful \u2013 but we often don\u2019t know how or why they work. Now, computer scientists are starting to peer inside their artificial minds.<\/p>\n<p>A PENNY for \u2019em? Knowing what someone is thinking is crucial for understanding their behaviour. It\u2019s the same with artificial intelligences. A new technique for taking snapshots of neural networks as they crunch through a problem will help us fathom how they work, leading to AIs that work better \u2013 and are more trustworthy.<\/p>\n<p>In the last few years, deep-learning algorithms built on neural networks \u2013 multiple layers of interconnected artificial neurons \u2013 have driven breakthroughs in many areas of artificial intelligence, including natural language processing, image recognition, medical diagnoses and beating a professional human player at the game Go.<\/p>\n<p>The trouble is that we don\u2019t always know how they do it. A deep-learning system is a black box, says Nir Ben Zrihem at the Israel Institute of Technology in Haifa. \u201cIf it works, great. If it doesn\u2019t, you\u2019re screwed.\u201d<\/p>\n<p>Neural networks are more than the sum of their parts. They are built from many very simple components \u2013 the artificial neurons. \u201cYou can\u2019t point to a specific area in the network and say all of the intelligence resides there,\u201d says Zrihem. But the complexity of the connections means that it can be impossible to retrace the steps a deep-learning algorithm took to reach a given result. In such cases, the machine acts as an oracle and its results are taken on trust.<\/p>\n<p>To address this, Zrihem and his colleagues created images of deep learning in action. The technique, they say, is like an fMRI for computers, capturing an algorithm\u2019s activity as it works through a problem. The images allow the researchers to track different stages of the neural network\u2019s progress, including dead ends.<\/p>\n<p><a href=\"https:\/\/www.newscientist.com\/article\/2077532-brain-scan-for-artificial-intelligence-shows-how-software-thinks\/\" target=\"_blank\">Read more<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Neural networks have become enormously successful \u2013 but we often don\u2019t know how or why they work. Now, computer scientists are starting to peer inside their artificial minds. A PENNY for \u2019em? Knowing what someone is thinking is crucial for understanding their behaviour. It\u2019s the same with artificial intelligences. A new technique for taking snapshots [\u2026]<\/p>\n","protected":false},"author":367,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[11,1523,41,6],"tags":[],"class_list":["post-22309","post","type-post","status-publish","format-standard","hentry","category-biotech-medical","category-computing","category-information-science","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/22309","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\/367"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=22309"}],"version-history":[{"count":2,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/22309\/revisions"}],"predecessor-version":[{"id":51015,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/22309\/revisions\/51015"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=22309"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=22309"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=22309"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}