{"id":70574,"date":"2017-06-30T22:22:28","date_gmt":"2017-07-01T05:22:28","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2017\/06\/microsoft-squeezed-ai-onto-a-raspberry-pi"},"modified":"2017-07-05T23:00:37","modified_gmt":"2017-07-06T06:00:37","slug":"microsoft-squeezed-ai-onto-a-raspberry-pi","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2017\/06\/microsoft-squeezed-ai-onto-a-raspberry-pi","title":{"rendered":"Microsoft squeezed AI onto a Raspberry Pi"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/microsoft-squeezed-ai-onto-a-raspberry-pi.jpg\"><\/a><\/p>\n<p>\u201cThe dominant paradigm is that these [sensor] devices are dumb,\u201d said senior researcher with Microsoft Research India, Manik Varma.<\/p>\n<p>Now, Varma\u2019s team in India and Microsoft researchers in Redmond, Washington, (the entire project is led by lead researcher Ofer Dekel) have figured out how to compress neural networks, the synapses of Machine Learning, down from 32 bits to, sometimes, a single bit and run them on a $10 <a href=\"http:\/\/%20(the%20entire%20project%20is%20led%20by%20Ofer%20Dekel)\" target=\"_blank\">Raspberry Pi<\/a>, a low-powered, credit-card-sized computer with a handful of ports and no screen. It\u2019s really just an open-source motherboard that can be deployed anywhere. The company announced the research in a <a href=\"https:\/\/blogs.microsoft.com\/next\/2017\/06\/29\/ais-big-leap-tiny-devices-opens-world-possibilities\/\" target=\"_blank\">blog post<\/a> on Thursday.<\/p>\n<p>Microsoft\u2019s work is part of a growing trend of moving Machine Learning closer to devices and end users.<\/p>\n<p><!-- Link: <a href=\"http:\/\/mashable.com\/2017\/06\/29\/microsoft-puts-ai-on-a-raspberry-pi\/?utm_cid=mash-com-fb-main-link#W2lQNASXtaqg\">http:\/\/mashable.com\/2017\/06\/29\/microsoft-puts-ai-on-a-raspbe...lQNASXtaqg<\/a> --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u201cThe dominant paradigm is that these [sensor] devices are dumb,\u201d said senior researcher with Microsoft Research India, Manik Varma. Now, Varma\u2019s team in India and Microsoft researchers in Redmond, Washington, (the entire project is led by lead researcher Ofer Dekel) have figured out how to compress neural networks, the synapses of Machine Learning, down from [\u2026]<\/p>\n","protected":false},"author":354,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-70574","post","type-post","status-publish","format-standard","hentry","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/70574","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\/354"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=70574"}],"version-history":[{"count":1,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/70574\/revisions"}],"predecessor-version":[{"id":70679,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/70574\/revisions\/70679"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=70574"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=70574"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=70574"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}