{"630778":{"#nid":"630778","#data":{"type":"event","title":"ML@GT Seminar: Ganesh Sundaramoorthi, United Technologies Research Center (UTRC)","body":[{"value":"\u003Cp\u003EML@GT invites you to a seminar by Ganesh Sundaramoorth, a principal research scientist\u0026nbsp;from United Technologies Research Center (UTRC).\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Ca href=\u0022https:\/\/docs.google.com\/forms\/d\/e\/1FAIpQLSeSaWo8qJd7-y55R3rppZ2MrArC2O-gtiLtvdqybhMRhaanrw\/viewform?usp=sf_link\u0022\u003ERSVP Here\u003C\/a\u003E\u0026nbsp;by Monday, February 10\u003C\/p\u003E\r\n\r\n\u003Ch3\u003ETalk Title\u003C\/h3\u003E\r\n\r\n\u003Cp\u003ESolving the Flickering Problem in Modern Convolutional Neural Networks\u003C\/p\u003E\r\n\r\n\u003Ch3\u003EAbstract\u003C\/h3\u003E\r\n\r\n\u003Cp\u003EDeep Learning has revolutionized the AI field.\u0026nbsp;\u0026nbsp; Despite this, there is much progress needed to deploy deep learning in safety critical applications (such as autonomous aircraft).\u0026nbsp; This is because current deep learning systems are not robust to real-world nuisances (e.g., viewpoint, illumination, partial occlusion).\u0026nbsp; In this talk, we take a step in constructing robust deep learning systems by addressing the problem that state-of-the-art Convolution Neural Networks (CNN) classifiers and detectors are vulnerable to small perturbations, including shifts of the image or camera.\u0026nbsp; While various forms of specially engineered\u0026nbsp;\u0026ldquo;adversarial perturbations\u0026rdquo; that fool deep learning systems have been well documented, modern CNNs can surprisingly change classification up to 30% probability even for simple 1-pixel shifts of the image.\u0026nbsp;This lack of translational stability seems to be partially the cause of \u0026ldquo;flickering\u0026rdquo; in state-of-the-art object detectors applied to video.\u0026nbsp; In this talk, we introduce this phenomena, propose a solution, prove it analytically, validate it empirically, and explain why existing CNNs exhibit this phenomena.\u003C\/p\u003E\r\n\r\n\u003Ch3\u003EBio\u003C\/h3\u003E\r\n\r\n\u003Cp\u003EGanesh Sundaramoorthi is currently Principal Research Scientist at\u0026nbsp;\u003Ca href=\u0022http:\/\/www.utrc.utc.com\/\u0022\u003EUnited Technologies Research Center\u003C\/a\u003E\u0026nbsp;in East Hartford, CT, USA, conducting research in computer vision and machine learning, and building products in robotic inspection from this research. Prior to this, he was Assistant Professor of Electrical Engineering and jointly Assistant Professor of Applied Mathematics and Computational Science at\u0026nbsp;\u003Ca href=\u0022https:\/\/www.kaust.edu.sa\/en\u0022\u003EKAUST\u003C\/a\u003E\u0026nbsp;starting in 2011. He directed the Computational Vision Lab at KAUST, which developed novel mathematics and algorithms, as well as software for video and image understanding technology. His fundamental optimization algorithms have led to advancements in motion-based video segmentation and detection. His group also developed technology for seismic image analysis, electron microscopy images, and medical (MRI \u0026amp; CT) images.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EPrior to KAUST, he was a postdoctoral research associate with\u0026nbsp;\u003Ca href=\u0022http:\/\/web.cs.ucla.edu\/~soatto\/\u0022\u003EProf.\u0026nbsp;Stefano Soatto\u003C\/a\u003E\u0026nbsp;in the Vision Lab at the University of California, Los Angeles from 2008 to 2010. There he made fundamental contributions to the view invariance problem in object recognition (with\u0026nbsp;\u003Ca href=\u0022http:\/\/www.math.ucla.edu\/~petersen\/\u0022\u003EProf. Peter Petersen\u003C\/a\u003E\u0026nbsp;and\u0026nbsp;\u003Ca href=\u0022https:\/\/en.wikipedia.org\/wiki\/Veeravalli_S._Varadarajan\u0022\u003EProf. V. S. Varadarajan\u003C\/a\u003E), and developed technology for video tracking. His PhD is in Electrical and Computer Engineering from the Georgia Institute of Technology in Atlanta, GA, USA in 2008. His PhD developed fundamental shape optimization methods for computer vision that aided in technology for video tracking, and medical image analysis. He was advised by\u0026nbsp;\u003Ca href=\u0022https:\/\/www.ece.gatech.edu\/faculty-staff-directory\/anthony-joseph-yezzi\u0022\u003EProf. Anthony Yezzi\u003C\/a\u003E. His Bachelor\u0026#39;s degrees were in Computer Engineering and Applied Mathematics, which he earned in 2003, also from Georgia Tech.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EHe has served as Area Chair for the leading computer vision conferences, including\u0026nbsp;\u003Ca href=\u0022https:\/\/en.wikipedia.org\/wiki\/Conference_on_Computer_Vision_and_Pattern_Recognition\u0022\u003EIEEE Conference on Computer Vision and Pattern Recognition\u003C\/a\u003E\u0026nbsp;(CVPR) and\u0026nbsp;\u003Ca href=\u0022https:\/\/en.wikipedia.org\/wiki\/International_Conference_on_Computer_Vision\u0022\u003EIEEE International Conference on Computer Vision\u003C\/a\u003E\u0026nbsp;(ICCV).\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"ML@GT invites you to a seminar by Ganesh Sundaramoorthi from United Technologies Research Center (UTRC)"}],"uid":"34773","created_gmt":"2020-01-08 18:23:09","changed_gmt":"2020-01-27 17:52:42","author":"ablinder6","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2020-02-12T12:15:00-05:00","event_time_end":"2020-02-12T13:15:00-05:00","event_time_end_last":"2020-02-12T13:15:00-05:00","gmt_time_start":"2020-02-12 17:15:00","gmt_time_end":"2020-02-12 18:15:00","gmt_time_end_last":"2020-02-12 18:15:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"47223","name":"College of Computing"},{"id":"37041","name":"Computational Science and Engineering"},{"id":"1299","name":"GVU Center"},{"id":"589608","name":"Machine Learning"},{"id":"576481","name":"ML@GT"},{"id":"431631","name":"OMS"},{"id":"50877","name":"School of Computational Science and Engineering"},{"id":"50875","name":"School of Computer Science"},{"id":"50876","name":"School of Interactive Computing"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1795","name":"Seminar\/Lecture\/Colloquium"}],"invited_audience":[{"id":"78761","name":"Faculty\/Staff"},{"id":"177814","name":"Postdoc"},{"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":[{"value":"\u003Cp\u003EKyla Hanson\u003C\/p\u003E\r\n\r\n\u003Cp\u003Ekhanson@cc.gatech.edu\u003C\/p\u003E\r\n","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}