{"id":145188,"date":"2022-08-30T14:23:52","date_gmt":"2022-08-30T19:23:52","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2022\/08\/robe-array-could-let-small-companies-access-popular-form-of-ai"},"modified":"2022-08-30T14:23:52","modified_gmt":"2022-08-30T19:23:52","slug":"robe-array-could-let-small-companies-access-popular-form-of-ai","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2022\/08\/robe-array-could-let-small-companies-access-popular-form-of-ai","title":{"rendered":"ROBE Array could let small companies access popular form of AI"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/robe-array-could-let-small-companies-access-popular-form-of-ai2.jpg\"><\/a><\/p>\n<p>A breakthrough low-memory technique by Rice University computer scientists could put one of the most resource-intensive forms of artificial intelligence\u2014deep-learning recommendation models (DLRM)\u2014within reach of small companies.<\/p>\n<p>DLRM recommendation systems are a popular form of AI that learns to make suggestions users will find relevant. But with top-of-the-line training models requiring more than a hundred terabytes of memory and supercomputer-scale processing, they\u2019ve only been available to a short list of technology giants with deep pockets.<\/p>\n<p>Rice\u2019s \u201crandom offset block embedding <a href=\"https:\/\/techxplore.com\/tags\/array\/\" rel=\"tag\" class=\"\">array<\/a>,\u201d or ROBE Array, could change that. It\u2019s an algorithmic approach for slashing the size of DLRM memory structures called embedding tables, and it will be presented this week at the Conference on Machine Learning and Systems (<a href=\"https:\/\/mlsys.org\/\">MLSys<\/a><a href=\"https:\/\/mlsys.org\/\"> 2022<\/a>) in Santa Clara, California, where it earned <a href=\"https:\/\/mlsys.org\/virtual\/2022\/session\/2180\">Outstanding Paper<\/a> honors.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>A breakthrough low-memory technique by Rice University computer scientists could put one of the most resource-intensive forms of artificial intelligence\u2014deep-learning recommendation models (DLRM)\u2014within reach of small companies. DLRM recommendation systems are a popular form of AI that learns to make suggestions users will find relevant. But with top-of-the-line training models requiring more than a hundred [\u2026]<\/p>\n","protected":false},"author":676,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[41,6,44],"tags":[],"class_list":["post-145188","post","type-post","status-publish","format-standard","hentry","category-information-science","category-robotics-ai","category-supercomputing"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/145188","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\/676"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=145188"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/145188\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=145188"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=145188"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=145188"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}