{"id":244,"date":"2006-12-12T19:40:31","date_gmt":"2006-12-13T01:40:31","guid":{"rendered":"http:\/\/hunch.net\/?p=244"},"modified":"2006-12-12T19:40:31","modified_gmt":"2006-12-13T01:40:31","slug":"interesting-papers-at-nips-2006","status":"publish","type":"post","link":"https:\/\/hunch.net\/?p=244","title":{"rendered":"Interesting Papers at NIPS 2006"},"content":{"rendered":"<p>Here are some papers that I found surprisingly interesting.<\/p>\n<ol>\n<li><a href=\"http:\/\/www.iro.umontreal.ca\/~bengioy\/\">Yoshua Bengio<\/a>, Pascal Lamblin, Dan Popovici, Hugo Larochelle, <a href=\"http:\/\/www.iro.umontreal.ca\/~lisa\/pointeurs\/dbn_supervised_tr1282.pdf\">Greedy Layer-wise Training of Deep Networks<\/a>. Empirically investigates some of the design choices behind deep belief networks.\n<\/li>\n<li><a href=\"http:\/\/www.stat.ucla.edu\/~lzhu\/\">Long Zhu<\/a>, Yuanhao Chen, <a href=\"http:\/\/www.stat.ucla.edu\/~yuille\/\">Alan Yuille<\/a> Unsupervised Learning of a Probabilistic Grammar for Object Detection and Parsing.  An unsupervised method for detecting objects using simple feature filters that works remarkably well on the (supervised) <a href=\"http:\/\/www.vision.caltech.edu\/Image_Datasets\/Caltech101\/Caltech101.html\">caltech-101 dataset<\/a>.<\/li>\n<li><a href=\"http:\/\/www.cs.uwaterloo.ca\/~shai\/\">Shai Ben-David<\/a>, <a href=\"http:\/\/www.cis.upenn.edu\/~blitzer\/\">John Blitzer<\/a>, <a href=\"http:\/\/www.cis.upenn.edu\/~crammer\/index.html\">Koby Crammer<\/a>, and <a href=\"http:\/\/www.cis.upenn.edu\/~pereira\/\">Fernando Pereira<\/a>, <a href=\"http:\/\/www.cis.upenn.edu\/~blitzer\/papers\/nips06.pdf\">Analysis of Representations for Domain Adaptation<\/a>.  This is the first analysis I&#8217;ve seen of learning with respect to samples drawn differently from the evaluation distribution which depends on reasonable measurable quantities.<\/li>\n<\/ol>\n<p>All of these papers turn out to have a common theme&#8212;the power of unlabeled data to do generically useful things.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Here are some papers that I found surprisingly interesting. Yoshua Bengio, Pascal Lamblin, Dan Popovici, Hugo Larochelle, Greedy Layer-wise Training of Deep Networks. Empirically investigates some of the design choices behind deep belief networks. Long Zhu, Yuanhao Chen, Alan Yuille Unsupervised Learning of a Probabilistic Grammar for Object Detection and Parsing. An unsupervised method for &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/hunch.net\/?p=244\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Interesting Papers at NIPS 2006&#8221;<\/span><\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[33,29,18,10],"tags":[],"class_list":["post-244","post","type-post","status-publish","format-standard","hentry","category-conferences","category-machine-learning","category-papers","category-unsupervised"],"_links":{"self":[{"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/posts\/244","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=244"}],"version-history":[{"count":0,"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/posts\/244\/revisions"}],"wp:attachment":[{"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=244"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=244"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=244"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}