{"52610":{"#nid":"52610","#data":{"type":"event","title":"NSF\/DHS FODAVA Distinguished Lecture","body":[{"value":"\u003Cp class=\u0022MsoPlainText\u0022\u003ENSF\/DHS FODAVA Distinguished Lecture\u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003E\u00a0\u003C\/p\u003E\n\u003Cp\u003EBy: Dr. Vladimir Vapnik\u003C\/p\u003E\n\u003Cp\u003ENEC Laboratories in Princeton, New Jersey, Columbia University, NY, NY and\u003C\/p\u003E\n\u003Cp\u003ERoyal Holloway, University of London, England\u003C\/p\u003E\n\u003Cp\u003EDate: Friday, January 16, 2009\u003C\/p\u003E\n\u003Cp\u003ETime: 2:00pm-3:00pm\u003C\/p\u003E\n\u003Cp\u003ELocation: Klaus 2447 \u003C\/p\u003E\n\u003Cp\u003EFor more information please contact \u00a0Dr. Haesun Park; \u003Ca href=\u0022mailto:hpark@cc.gatech.edu\u0022\u003Ehpark@cc.gatech.edu\u003C\/a\u003E\u003C\/p\u003E\n\u003Cp\u003E\u00a0\u003C\/p\u003E\n\u003Cp\u003E\u00a0\u003C\/p\u003E\n\u003Cp\u003ETitle:\u003C\/p\u003E\n\u003Cp\u003ELearning with Teacher:\u00a0 Learning Using Hidden Information\u003C\/p\u003E\n\u003Cp\u003E\u00a0\u003C\/p\u003E\n\u003Cp\u003EAbstract: \u003C\/p\u003E\n\u003Cp\u003EThe existing machine learning paradigm considers a simple\u003Cbr \/\u003Escheme: given a set of training examples\u00a0find in a given collection of functions\u003Cbr \/\u003Ethe one that in the best possible way approximates the unknown\u003Cbr \/\u003Edecision rule. In such a paradigm a teacher does not play an important role.\u003C\/p\u003E\n\u003Cp\u003EIn human learning, however, the role of a teacher is very important:\u003Cbr \/\u003Ealong with examples a teacher provides students with explanations,\u003Cbr \/\u003Ecomments, comparisons, and so on.\u003C\/p\u003E\n\u003Cp\u003EIn this\u00a0talk I\u00a0will\u00a0 introduce elements of human teaching in machine learning.\u00a0\u003C\/p\u003E\n\u003Cp\u003EI will consider an advanced learning paradigm called learning using hidden information\u003Cbr \/\u003E(LUHI), where at the training stage a teacher gives some additional information $x^*$ about training example $x$. This information will not be available at the test stage.\u003C\/p\u003E\n\u003Cp\u003EI\u00a0will\u00a0consider the LUHI paradigm\u00a0 for support vector machine type of algorithms, demonstrate its superiority over the classical one and discuss general questions related to this paradigm.\u003C\/p\u003E\n\u003Cp\u003E\u00a0\u003C\/p\u003E\n\u003Cp\u003EBio: \u003C\/p\u003E\n\u003Cp\u003EVladimir Naumovich Vapnik is one of the main developers of Vapnik-Chervonenkis theory. He was born in the Soviet Union. He received his master\u0027s degree in mathematics at the Uzbek State University, Samarkand, Uzbek SSR in 1958 and \u003Ca title=\u0022Doctor of Philosophy\u0022 href=\u0022http:\/\/en.wikipedia.org\/wiki\/Doctor_of_Philosophy\u0022\u003EPh.D\u003C\/a\u003E in statistics at the Institute of Control Sciences, Moscow in 1964. He worked at this institute from 1961 to 1990 and became Head of the Computer Science Research Department. At the end of 1990, he moved to the USA and joined the Adaptive Systems Research Department at AT\u0026amp;T Bell Labs in Holmdel, New Jersey. The group later became the Image Processing Research Department of AT\u0026amp;T Laboratories when AT\u0026amp;T spun off Lucent Technologies in 1996. Vapnik Left AT\u0026amp;T in 2002 and joined NEC Laboratories in Princeton, New Jersey, where he currently works in the Machine Learning group. He also holds a Professor of Computer Science and Statistics position at Royal Holloway, University of London since 1995, as well as an Adjunct Professor position at Columbia University, New York City since 2003. He was inducted into the U.S. National Academy of Engineering in 2006. While at AT\u0026amp;T, Vapnik and his colleagues developed the theory of the support vector machine. They demonstrated its performance on a number of problems of interest to the machine learning community, including handwriting recognition.\u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003EThis event is sponsored by NSF\/DHS FODAVA grant, School of Mathematics, Division of Computational Science and Engineering, Algorithms and Randomness Center, and Machine Learning and Data Mining Seminar Series grant by Yahoo.\u003C\/p\u003E\n\u003Cp\u003E\u00a0\u003C\/p\u003E\n\u003Cp\u003E~~~~~~~~~~~~~~~~~~\u003C\/p\u003E\n\u003Cp\u003E\u00a0\u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003EYou are cordially invited to attend a reception that will follow the seminar to chat informally with faculty and students. Refreshments will be provided.\u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003E\u00a0\u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003ETo receive future announcements, please sign up to the cse-seminar email list:\u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003E\u00a0\u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003E\u003Ca title=\u0022https:\/\/mailman.cc.gatech.edu\/mailman\/listinfo\/cse-seminar\u0022 href=\u0022https:\/\/mailman.cc.gatech.edu\/mailman\/listinfo\/cse-seminar\u0022\u003Ehttps:\/\/mailman.cc.gatech.edu\/mailman\/listinfo\/cse-seminar\u003C\/a\u003E\u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003E\u00a0\u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003EHope to see you there!\u003C\/p\u003E\n\u003Cp\u003E\u00a0\u003C\/p\u003E\n\u003Cp\u003E\u003C\/p\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":"","uid":"27154","created_gmt":"2010-02-11 15:56:37","changed_gmt":"2016-10-08 01:49:56","author":"Louise Russo","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2009-01-16T13:00:00-05:00","event_time_end":"2009-01-16T14:00:00-05:00","event_time_end_last":"2009-01-16T14:00:00-05:00","gmt_time_start":"2009-01-16 18:00:00","gmt_time_end":"2009-01-16 19:00:00","gmt_time_end_last":"2009-01-16 19:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"47223","name":"College of Computing"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"Lometa Mitchell","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}