{"626704":{"#nid":"626704","#data":{"type":"event","title":"PhD Defense by Minsuk Brian Kahng","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle\u003C\/strong\u003E: Human-Centered AI through Scalable Visual Data Analytics\u003Cbr \/\u003E\r\n\u0026nbsp;\u003Cbr \/\u003E\r\nMinsuk Brian Kahng\u003Cbr \/\u003E\r\nComputer Science PhD Student\u003Cbr \/\u003E\r\nSchool of Computational Science and Engineering\u003Cbr \/\u003E\r\nCollege of Computing\u003Cbr \/\u003E\r\nGeorgia Institute of Technology\u003Cbr \/\u003E\r\n\u003Ca href=\u0022https:\/\/minsuk.com\u0022\u003Ehttps:\/\/minsuk.com\u003C\/a\u003E\u003Cbr \/\u003E\r\n\u0026nbsp;\u003Cbr \/\u003E\r\n\u003Cstrong\u003EDate\u003C\/strong\u003E: Tuesday, October 8th, 2019\u003Cbr \/\u003E\r\n\u003Cstrong\u003ETime\u003C\/strong\u003E: 10:00am to 12:00pm (EDT)\u003Cbr \/\u003E\r\n\u003Cstrong\u003ELocation\u003C\/strong\u003E: Coda 114 (756 West Peachtree St NW)\u003Cbr \/\u003E\r\n\u0026nbsp;\u003Cbr \/\u003E\r\n\u003Cstrong\u003ECommittee\u003C\/strong\u003E:\u003Cbr \/\u003E\r\n----------------\u003Cbr \/\u003E\r\nDr. Polo Chau (Advisor, School of Computational Science and Engineering, Georgia Institute of Technology)\u003Cbr \/\u003E\r\nDr. Sham Navathe (School of Computer Science, Georgia Institute of Technology)\u003Cbr \/\u003E\r\nDr. Alex Endert (School of Interactive Computing, Georgia Institute of Technology)\u003Cbr \/\u003E\r\nDr. Martin Wattenberg (Senior Staff Research Scientist, Google)\u003Cbr \/\u003E\r\nDr. Fernanda Vi\u0026eacute;gas (Senior Staff Research Scientist, Google)\u003Cbr \/\u003E\r\n\u0026nbsp;\u003Cbr \/\u003E\r\n\u003Cstrong\u003EAbstract\u003C\/strong\u003E:\u003Cbr \/\u003E\r\n----------------\u003Cbr \/\u003E\r\nWhile artificial intelligence (AI) has led to major breakthroughs in many domains, understanding machine learning models remains a fundamental challenge. How can we make AI more accessible and interpretable, or more broadly, human-centered, so that people can easily understand and effectively use these complex models?\u003Cbr \/\u003E\r\n\u0026nbsp;\u003Cbr \/\u003E\r\nMy dissertation addresses these fundamental and practical challenges in AI through a human-centered approach, by creating novel data visualization tools that are scalable, interactive, and easy to learn and to use. With such tools, users can better understand models by visually exploring how large input datasets affect the models and their results. Specifically, my dissertation focuses on three interrelated parts:\u003Cbr \/\u003E\r\n(1) \u003Cstrong\u003EUnified scalable interpretation\u003C\/strong\u003E: developing scalable visual analytics tools that help engineers interpret industry-scale deep learning models at both instance- and subset-level (e.g., ActiVis deployed by Facebook);\u003Cbr \/\u003E\r\n(2) \u003Cstrong\u003EInsight discovery in workflow\u003C\/strong\u003E: designing visual data exploration tools that support discovery of insights through exploration of data groups over different analytics stages, such as model comparison (e.g., MLCube) and fairness auditing (e.g., FairVis); and\u003Cbr \/\u003E\r\n(3) \u003Cstrong\u003ELearning complex models by experimentation\u003C\/strong\u003E: building interactive tools that broaden people\u0026#39;s access to learning complex deep learning models (e.g., GAN Lab) and browsing raw datasets (e.g., ETable).\u003Cbr \/\u003E\r\n\u0026nbsp;\u003Cbr \/\u003E\r\nMy research has made significant impact to society and industry. The ActiVis system for interpreting deep learning models has been deployed on Facebook\u0026#39;s machine learning platform. The GAN Lab tool for learning GANs has been open-sourced in collaboration with Google, with its demo used by more than 70,000 people from over 160 countries.\u003Cbr \/\u003E\r\n\u003Cbr \/\u003E\r\n\u0026nbsp;\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Human-Centered AI through Scalable Visual Data Analytics"}],"uid":"27707","created_gmt":"2019-09-25 02:13:07","changed_gmt":"2019-09-25 02:13:07","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2019-10-08T11:00:00-04:00","event_time_end":"2019-10-08T13:00:00-04:00","event_time_end_last":"2019-10-08T13:00:00-04:00","gmt_time_start":"2019-10-08 15:00:00","gmt_time_end":"2019-10-08 17:00:00","gmt_time_end_last":"2019-10-08 17:00:00","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":"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":""}}}