{"627455":{"#nid":"627455","#data":{"type":"event","title":"PhD Defense by Arjun Chandrasekaran","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle\u003C\/strong\u003E: Towards natural Human-AI interactions in Vision and Language\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EArjun Chandrasekaran\u003C\/p\u003E\r\n\r\n\u003Cp\u003EComputer Science PhD Student\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\u003Ca href=\u0022http:\/\/www.prism.gatech.edu\/~arjun9\/\u0022\u003Ehttp:\/\/www.prism.gatech.edu\/~arjun9\/\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EDate\u003C\/strong\u003E: Monday, October 21st, 2019\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ETime\u003C\/strong\u003E:\u0026nbsp; 12pm to 2pm (EDT)\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ELocation\u003C\/strong\u003E: Coda 1215 \u0026ldquo;Midtown\u0026rdquo; (756 West Peachtree St NW)\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\u003E----------------\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Devi Parikh (Advisor, College of Computing, Georgia Institute of Technology)\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Dhruv Batra (College of Computing, Georgia Institute of Technology)\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Sonia Chernova (College of Computing, Georgia Institute of Technology)\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Mark Riedl (College of Computing, Georgia Institute of Technology)\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Mohit Bansal (Department of Computer Science, University of North Carolina at Chapel Hill)\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\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\u003E----------------\u003C\/p\u003E\r\n\r\n\u003Cp\u003EInter-human interaction is a rich form of communication. Human interactions typically leverage a good theory of mind, involve pragmatics, story-telling, humor, sarcasm, empathy, sympathy, etc. Recently, we have seen a tremendous increase in the frequency and the modalities through which humans interact with AI. Despite this, current human-AI interactions lack many of these features that characterize inter-human interactions. Towards the goal of developing AI that can interact with humans naturally (similar to other humans), I take a two-pronged approach that involves investigating the ways in which both the AI and the human can adapt to each other\u0026rsquo;s characteristics and capabilities. In my research, I study aspects\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003Eof human interactions, such as humor, story-telling, and the humans\u0026rsquo; abilities to understand and collaborate with an AI. Specifically, in the vision and language modalities,\u003C\/p\u003E\r\n\r\n\u003Col\u003E\r\n\t\u003Cli\u003EIn an effort to improve the AI\u0026rsquo;s capabilities to adapt its interactions to a human, we build computational models for (i) humor manifested in static images, (ii) contextual, multi-modal humor, and (iii) temporal understanding of the elements of a story\u003Cstrong\u003E.\u0026nbsp;\u003C\/strong\u003E\u003C\/li\u003E\r\n\t\u003Cli\u003EIn an effort to improve the capabilities of a collaborative human-AI team, we study (i) a lay person\u0026rsquo;s predictions regarding the behavior of an AI in a situation, (ii) the extent to which interpretable explanations from an AI can improve performance of a human-AI team.\u0026nbsp;\u003C\/li\u003E\r\n\u003C\/ol\u003E\r\n\r\n\u003Cp\u003EThrough this work, I demonstrate that aspects of human interactions (such as certain forms of humor and story-telling) can be modeled with reasonable success using computational models that utilize neural networks. On the other hand, I also show that a lay person can successfully predict the outputs and failures of a deep neural network. Finally, I present evidence that suggests that a lay person who has access to interpretable explanations from the model, can collaborate more effectively with a neural network on a goal-driven task.\u0026nbsp;\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Towards natural Human-AI interactions in Vision and Language"}],"uid":"27707","created_gmt":"2019-10-10 14:26:41","changed_gmt":"2019-10-10 14:26:41","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2019-10-21T13:00:00-04:00","event_time_end":"2019-10-21T15:00:00-04:00","event_time_end_last":"2019-10-21T15:00:00-04:00","gmt_time_start":"2019-10-21 17:00:00","gmt_time_end":"2019-10-21 19:00:00","gmt_time_end_last":"2019-10-21 19:00:00","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":"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":""}}}