{"615172":{"#nid":"615172","#data":{"type":"event","title":"Phd Proposal by Ramprasaath R. Selvaraju","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle:\u003C\/strong\u003E\u0026nbsp;Towards Interpretable, Transparent and Unbiased AI\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EDate\u003C\/strong\u003E: Tuesday, December 11 2018\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ETime\u003C\/strong\u003E: 4:30PM - 6:30PM (ET)\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ELocation\u003C\/strong\u003E:\u0026nbsp;\u003Cstrong\u003ECCB 312A\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003ERamprasaath R. Selvaraju\u003C\/p\u003E\r\n\r\n\u003Cp\u003EPh.D. Student in Computer Science\u003C\/p\u003E\r\n\r\n\u003Cp\u003ESchool of Interactive Computing\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EGeorgia Institute of Technology\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Ca href=\u0022http:\/\/ramprs.github.io\/\u0022\u003Eramprs.github.io\u003C\/a\u003E\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, Georgia Institute of Technology)\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Dhruv Batra (School of Interactive Computing, Georgia Institute of Technology)\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Stefan Lee (School of Interactive Computing, Georgia Institute of Technology)\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Been Kim (Sr. Research Scientist, Google Brain)\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\u003EDeep networks have enabled unprecedented breakthroughs in a variety of computer vision tasks. While these models enable superior performance, their increasing complexity and lack of decomposability into individually intuitive components makes them hard to interpret. Consequently, when today\u0026#39;s intelligent systems fail, they fail spectacularly disgracefully, giving no warning or explanation.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003ETowards the goal of making deep networks Interpretable, Transparent and Unbiased, in my thesis I will present my work on building algorithms that provide explanations for decisions emanating from deep networks in order to \u0026mdash;\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E1. understand why the model did what it did,\u003C\/p\u003E\r\n\r\n\u003Cp\u003E2. diagnose network errors,\u003C\/p\u003E\r\n\r\n\u003Cp\u003E3. help users build appropriate trust, and\u003C\/p\u003E\r\n\r\n\u003Cp\u003E4. enable knowledge transfer between humans and AI.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EIn my proposed work, I will show how we can leverage explanations to teach AI systems to correct unwanted biases learned during training, thus improving visual grounding in these systems and making them more trustworthy.\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Towards Interpretable, Transparent and Unbiased AI"}],"uid":"27707","created_gmt":"2018-12-10 14:05:10","changed_gmt":"2018-12-10 14:05:10","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2018-12-11T16:30:00-05:00","event_time_end":"2018-12-11T18:30:00-05:00","event_time_end_last":"2018-12-11T18:30:00-05:00","gmt_time_start":"2018-12-11 21:30:00","gmt_time_end":"2018-12-11 23:30:00","gmt_time_end_last":"2018-12-11 23:30:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"102851","name":"Phd proposal"}],"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":""}}}