{"id":283880,"date":"2016-03-15T11:26:13","date_gmt":"2016-03-15T18:26:13","guid":{"rendered":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/?post_type=msr-research-item&#038;p=283880"},"modified":"2016-08-26T11:28:08","modified_gmt":"2016-08-26T18:28:08","slug":"parallel-inference-learning-deep-structured-distributions","status":"publish","type":"msr-video","link":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/video\/parallel-inference-learning-deep-structured-distributions\/","title":{"rendered":"Parallel Inference and Learning with Deep Structured Distributions"},"content":{"rendered":"<p>Many problems in real-world applications involve predicting several random variables which are statistically related. A structured model, like a Markov random field, is a great mathematical tool to encode those dependencies. Within the first part of this talk I will discuss the difficulties in finding the most likely configuration described by a structured distribution. I will present a model-parallel inference algorithm and illustrate its effectiveness in jointly estimating the disparity of more than 12 million variables. In the second part, I will show how to combine structured distributions with deep learning to estimate complex representations which take into account the dependencies between the random variables. To model those deep structured distributions I will present a sample-parallel training algorithm and show its applicability, among others, by using a 3D scene understanding task.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Many problems in real-world applications involve predicting several random variables which are statistically related. A structured model, like a Markov random field, is a great mathematical tool to encode those dependencies. Within the first part of this talk I will discuss the difficulties in finding the most likely configuration described by a structured distribution. I [&hellip;]<\/p>\n","protected":false},"featured_media":275697,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr_hide_image_in_river":0,"footnotes":""},"research-area":[13561,13546],"msr-video-type":[],"msr-locale":[268875],"msr-post-option":[],"msr-session-type":[],"msr-impact-theme":[],"msr-pillar":[],"msr-episode":[],"msr-research-theme":[],"class_list":["post-283880","msr-video","type-msr-video","status-publish","has-post-thumbnail","hentry","msr-research-area-algorithms","msr-research-area-computational-sciences-mathematics","msr-locale-en_us"],"msr_download_urls":"","msr_external_url":"https:\/\/youtu.be\/kUPxtUS06fY","msr_secondary_video_url":"","msr_video_file":"","_links":{"self":[{"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/283880","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-video"}],"about":[{"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-video"}],"version-history":[{"count":0,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/283880\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media\/275697"}],"wp:attachment":[{"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=283880"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=283880"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=283880"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=283880"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=283880"},{"taxonomy":"msr-session-type","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-session-type?post=283880"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=283880"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=283880"},{"taxonomy":"msr-episode","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-episode?post=283880"},{"taxonomy":"msr-research-theme","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-theme?post=283880"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}