{"652971":{"#nid":"652971","#data":{"type":"event","title":"Ph.D. Dissertation Defense - Mohit Prabhushankar","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle\u003C\/strong\u003E\u003Cem\u003E:\u0026nbsp; \u003C\/em\u003E\u003Cem\u003EContrastive Reasoning in Neural Networks\u003C\/em\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ECommittee:\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Ghassan AlRegib, ECE, Chair, Advisor\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Mark Davenport, ECE\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Mark Riedl, CoC\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Larry Heck, ECE\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Eva Dyer, BME\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAbstract: \u003C\/strong\u003EThe objective of the dissertation is to rethink the inductive nature of reasoning in neural networks by providing contextual explanations to a network\u0026#39;s decision and addressing the network\u0026#39;s robustness capabilities. Neural networks represent data as projections on trained weights in a high dimensional manifold. The trained weights act as a knowledge base consisting of causal class dependencies. Inference built on features that identify dependencies within this manifold is termed as inductive feed-forward inference. This is a classical cause-to-effect inference model that is widely used because of its simple mathematical functionality and ease of operation. Nevertheless, feed-forward models do not generalize well to untrained situations. To alleviate this generalization challenge, we use an effect-to-cause inference model that falls under the abductive reasoning framework. Here, the features represent the change from existing weight dependencies given a certain effect. In this dissertation, we term this change as contrast and the ensuing inference mechanism as contrastive inference. The dissertation tackles contrastive reasoning and inference in three phases: 1) We formalize the structure of contrastive reasons as answers to questions of the form \u0026middot;why P, rather than Q?\u0026#39; and provide a simple mechanism to extract contrastive reasons from any pre-trained neural network, 2) We analyze our contrastive reasons by creating a taxonomy of evaluation, and 3) Use contrastive reasons to make robust and generalizable decisions. We provide representational and explanatory insights using our contrastive reasoning scheme for diverse visual applications including: 1) Visual cognition-based human attention, 2) P robabilistic modeling of causal and context features, 3) Active learning paradigm of machine learning, and 4) Meta-representations within neural networks.\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Contrastive Reasoning in Neural Networks "}],"uid":"28475","created_gmt":"2021-11-17 21:10:41","changed_gmt":"2021-11-17 21:14:00","author":"Daniela Staiculescu","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2021-12-03T15:00:00-05:00","event_time_end":"2021-12-03T17:00:00-05:00","event_time_end_last":"2021-12-03T17:00:00-05:00","gmt_time_start":"2021-12-03 20:00:00","gmt_time_end":"2021-12-03 22:00:00","gmt_time_end_last":"2021-12-03 22:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"434381","name":"ECE Ph.D. Dissertation Defenses"}],"categories":[],"keywords":[{"id":"100811","name":"Phd Defense"},{"id":"1808","name":"graduate students"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}