{"id":70492,"date":"2017-06-24T07:03:19","date_gmt":"2017-06-24T14:03:19","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2017\/06\/mit-and-google-researchers-have-made-ai-that-can-link-sound-sight-and-text-to-understand-the-world"},"modified":"2017-06-24T07:03:19","modified_gmt":"2017-06-24T14:03:19","slug":"mit-and-google-researchers-have-made-ai-that-can-link-sound-sight-and-text-to-understand-the-world","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2017\/06\/mit-and-google-researchers-have-made-ai-that-can-link-sound-sight-and-text-to-understand-the-world","title":{"rendered":"MIT and Google researchers have made AI that can link sound, sight, and text to understand the world"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/mit-and-google-researchers-have-made-ai-that-can-link-sound-sight-and-text-to-understand-the-world.jpg\"><\/a><\/p>\n<p>If we ever want future robots to do our bidding, they\u2019ll have to understand the world around them in a complete way\u2014if a robot hears a barking noise, what\u2019s making it? What does a dog look like, and what do dogs need?<\/p>\n<p>AI research has typically treated the ability to recognize images, identify noises, and understand text as three different problems, and built algorithms suited to each individual task. Imagine if you could only use one sense at a time, and couldn\u2019t match anything you heard to anything you saw. That\u2019s AI today, and part of the reason why we\u2019re so far from creating an algorithm that can learn like a human. But two new papers from <a href=\"https:\/\/arxiv.org\/abs\/1706.00932\">MIT<\/a> and <a href=\"https:\/\/arxiv.org\/abs\/1706.05137\">Google<\/a> explain first steps for making AI see, hear, and read in a holistic way\u2014an approach that could upend how we teach our machines about the world.<\/p>\n<p>\u201cIt doesn\u2019t matter if you see a car or hear an engine, you instantly recognize the same concept. The information in our brain is aligned naturally,\u201d says <a href=\"https:\/\/people.csail.mit.edu\/yusuf\/\">Yusuf Aytar<\/a>, a post-doctoral AI research at MIT who co-authored the paper.<\/p>\n<p><!-- Link: <a href=\"https:\/\/qz.com\/1011641\/mit-and-google-researchers-have-made-ai-that-can-link-sound-sight-and-text-to-understand-the-world\/\">https:\/\/qz.com\/1011641\/mit-and-google-researchers-have-made-...the-world\/<\/a> --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>If we ever want future robots to do our bidding, they\u2019ll have to understand the world around them in a complete way\u2014if a robot hears a barking noise, what\u2019s making it? What does a dog look like, and what do dogs need? AI research has typically treated the ability to recognize images, identify noises, and [\u2026]<\/p>\n","protected":false},"author":354,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[41,6],"tags":[],"class_list":["post-70492","post","type-post","status-publish","format-standard","hentry","category-information-science","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/70492","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=70492"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/70492\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=70492"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=70492"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=70492"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}