{"612535":{"#nid":"612535","#data":{"type":"event","title":"PhD Defense by Shanmukha Ramakrishna Vedantam","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle:\u003C\/strong\u003E Interpretation, Grounding, and Imagination for Machine\u003Cbr \/\u003E\r\nIntelligence\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EShanmukha Ramakrishna Vedantam\u003C\/p\u003E\r\n\r\n\u003Cp\u003EPh.D. Student\u003C\/p\u003E\r\n\r\n\u003Cp\u003ESchool of Interactive Computing\u003C\/p\u003E\r\n\r\n\u003Cp\u003ECollege of Computing\u003C\/p\u003E\r\n\r\n\u003Cp\u003EGeorgia Institute of Technology\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDate: Wednesday, October 24, 2018\u003C\/p\u003E\r\n\r\n\u003Cp\u003ETime: 5:30PM - 7:30PM (EDT)\u003C\/p\u003E\r\n\r\n\u003Cp\u003ELocation: College of Computing Building (CCB) Room 312A\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ECommittee:\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Devi Parikh (Advisor, School of Interactive Computing,\u003Cbr \/\u003E\r\nGeorgia Institute of Technology)\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Dhruv Batra (School of Interactive Computing, Georgia\u003Cbr \/\u003E\r\nInstitute of Technology)\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Jacob Eisenstein (School of Interactive Computing, Georgia\u003Cbr \/\u003E\r\nInstitute of Technology)\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Kevin P. Murphy (Research Scientist, Google Research)\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. C. Lawrence Zitnick (Research Manager, Facebook AI Research)\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAbstract:\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EUnderstanding how to model computer vision and natural language\u003Cbr \/\u003E\r\njointly is a long-standing challenge in artificial intelligence. In this\u003Cbr \/\u003E\r\nthesis, I study how modeling vision and language using semantic and pragmatic\u003Cbr \/\u003E\r\nconsiderations can help derive more human-like inferences from machine learning\u003Cbr \/\u003E\r\nmodels. Specifically, I consider three related problems: interpretation,\u003Cbr \/\u003E\r\ngrounding, and imagination.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EIn interpretation, the goal is to get machine learning models to\u003Cbr \/\u003E\r\nunderstand an image and describe its contents using natural language in a\u003Cbr \/\u003E\r\ncontextually relevant manner. In grounding, I study how to connect natural\u003Cbr \/\u003E\r\nlanguage to referents in the physical world, and understand if this can help\u003Cbr \/\u003E\r\nlearn common sense. Finally, in imagination, I study how to \u0026lsquo;imagine\u0026rsquo; visual\u003Cbr \/\u003E\r\nconcepts completely and accurately across the full range and (potentially\u003Cbr \/\u003E\r\nunseen) compositions of their visual attributes. I will analyze these problems\u003Cbr \/\u003E\r\nfrom computational as well as algorithmic perspectives and suggest exciting\u003Cbr \/\u003E\r\ndirections for future work.\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Interpretation, Grounding, and Imagination for Machine Intelligence"}],"uid":"27707","created_gmt":"2018-10-10 15:37:56","changed_gmt":"2018-10-10 15:37:56","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2018-10-24T18:30:00-04:00","event_time_end":"2018-10-24T20:30:00-04:00","event_time_end_last":"2018-10-24T20:30:00-04:00","gmt_time_start":"2018-10-24 22:30:00","gmt_time_end":"2018-10-25 00:30:00","gmt_time_end_last":"2018-10-25 00:30:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"100811","name":"Phd Defense"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78761","name":"Faculty\/Staff"},{"id":"78771","name":"Public"},{"id":"174045","name":"Graduate students"},{"id":"78751","name":"Undergraduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}