{"id":78,"date":"2008-07-20T23:04:06","date_gmt":"2008-07-21T06:04:06","guid":{"rendered":"https:\/\/www.wkiri.com\/today\/?p=78"},"modified":"2008-07-20T23:04:06","modified_gmt":"2008-07-21T06:04:06","slug":"artificial-intelligence-not-for-fruit-flies","status":"publish","type":"post","link":"https:\/\/www.wkiri.com\/today\/?p=78","title":{"rendered":"Artificial Intelligence (not for fruit flies)"},"content":{"rendered":"<p><img decoding=\"async\" align=right src=\"http:\/\/www.aaai.org\/styles\/images\/aaai-logo.jpg\">I recently attended the annual <a href=\"http:\/\/www.aaai.org\/Conferences\/AAAI\/aaai08.php\">Conference on Artificial Intelligence<\/a>, held this year in Chicago, IL.  I took away several new ideas and thoughts.  Here are some highlights:<\/p>\n<ul>\n<li><a href=\"http:\/\/www.cs.cmu.edu\/~efros\/\">Alyosha Efros<\/a> gave his invited talk on a variety of cool things you can do with a single image&#8211;from <a href=\"http:\/\/www.cs.uiuc.edu\/homes\/dhoiem\/projects\/popup\/index.html\">inferring 3D geometry<\/a> to <a href=\"http:\/\/graphics.cs.cmu.edu\/projects\/scene-completion\/\">automatically filling in occluded parts<\/a> to <a href=\"http:\/\/graphics.cs.cmu.edu\/projects\/im2gps\/\">estimating the location where the image was taken<\/a>, all of his work is exciting even if you&#8217;re not a computer vision researcher.  (Bonus: how to <a href=\"http:\/\/graphics.cs.cmu.edu\/projects\/imageshaving\/\">digitally &#8220;shave&#8221;<\/a>)\n<li><a href=\"http:\/\/www.cs.berkeley.edu\/~russell\/\">Stuart Russell<\/a> noted that the graduate Machine Learning course at Berkeley has the largest enrollment of any grad course in the entire university; enrollment has reached as high as 140 students.  In his invited talk, he issued a call to arms motivating AI researchers to tackle bigger research problems.  &#8220;Fruit flies can recognize digits!&#8221; he noted.  He urged the development of agents with probabilistic first-order logic, that track their internal state, and have the ability to abstract both behavior and their lookahead abilities.  Ambitious, of course!\n<li>Two presentations discussed methods for training a learning algorithm with zero data.  No, really!  Both pointed out problems in which the class labels or identities themselves can be represented in feature space, so you don&#8217;t really need to further train on real data.  This is pretty obvious&#8211;effectively, it&#8217;s for problems where you already have a class prototype or representative, which is one way to represent a learned model anyway&#8211;but I think the papers are still useful in that they cause us to stop and think about what we can leverage a priori, instead of just hunting for more and more training data.\n<li>Explicit Semantic Analysis (ESA) is an interesting text analysis technique that is useful when analyzing short text snippets, like keywords or web search queries.  There isn&#8217;t much content in a two-word phrase, but ESA can remedy that by searching for the phrase in wikipedia and then expanding the &#8220;semantic content&#8221; (or representation) of the phrase using the titles of all wikipedia articles that contain it.  Pretty clever!\n<\/ul>\n<p>I also co-chaired the <a href=\"http:\/\/www.cs.hmc.edu\/aieducation\/\">Colloquium on AI Education<\/a>, which was very well attended, energizing, and fun.  I may even talk myself into doing some teaching again this year. :)<\/p>\n","protected":false},"excerpt":{"rendered":"<p>I recently attended the annual Conference on Artificial Intelligence, held this year in Chicago, IL. I took away several new ideas and thoughts. Here are some highlights: Alyosha Efros gave his invited talk on a variety of cool things you can do with a single image&#8211;from inferring 3D geometry to automatically filling in occluded parts [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[23],"tags":[],"_links":{"self":[{"href":"https:\/\/www.wkiri.com\/today\/index.php?rest_route=\/wp\/v2\/posts\/78"}],"collection":[{"href":"https:\/\/www.wkiri.com\/today\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.wkiri.com\/today\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.wkiri.com\/today\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.wkiri.com\/today\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=78"}],"version-history":[{"count":0,"href":"https:\/\/www.wkiri.com\/today\/index.php?rest_route=\/wp\/v2\/posts\/78\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.wkiri.com\/today\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=78"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wkiri.com\/today\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=78"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wkiri.com\/today\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=78"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}