Towards Explainable, Adaptive, and Active Deep Learning
Date: 2019/12/02 - 2019/12/02
Academic Seminar: Towards Explainable, Adaptive, and Active Deep Learning
Speaker: Prof. Trevor Darrell, UC Berkeley
Time: 01:30 p.m.- 02:30 p.m., December 2nd, 2019 (Monday)
Location: CIMC Auditorium – 300, Long Bin Building, Shanghai Jiao Tong University Minhang Campus
Abstract
Deep Learning has provided significant advances in computer vision and robotics in recent years, but has traditionally been limited to fully supervised settings with very large amounts of training data or explciit reward, where the learned models lacked interpretability. New results in adversarial adaptive representation learning show how such methods can also excel when learning across modalities and domains, and further can be trained or constrained to provide natural language explanations and/or reveal internal structure. Time permitting, I'll also present recent compositional network models that learn instance-specific network structures to solve individual tasks, and models for active learning based on adversarial representation learning, as well as progress on video captioning and recognition challenges.
Biography
Prof. Darrell is on the faculty of the CS and EE Divisions of the EECS Department at UC Berkeley. He leads Berkeley’s DeepDrive (BDD) Industrial Consortia, is co-Director of the Berkeley Artificial Intelligence Research (BAIR) lab, and is Faculty Director of PATH at UC Berkeley. Darrell’s group develops algorithms for large-scale perceptual learning, including object and activity recognition and detection, for a variety of applications including autonomous vehicles, media search, and multimodal interaction with robots and mobile devices. His areas of interest include computer vision, machine learning, natural language processing, and perception-based human computer interfaces. Prof. Darrell previously led the vision group at the International Computer Science Institute in Berkeley, and was on the faculty of the MIT EECS department from 1999-2008, where he directed the Vision Interface Group. He was a member of the research staff at Interval Research Corporation from 1996-1999, and received the S.M., and PhD. degrees from MIT in 1992 and 1996, respectively. He obtained the B.S.E. degree from the University of Pennsylvania in 1988.
Prof. Darrell also serves as consulting Chief Scientist for the start-up Nexar, and is a technical consultant on deep learning and computer vision for Pinterest. Darrell is on the scientific advisory board of several other ventures, including DeepScale, WaveOne, SafelyYou, and Graymatics. Previously, Darrell advised Tyzx (acquired by Intel), IQ Engines (acquired by Yahoo), Koozoo, BotSquare/Flutter (acquired by Google), and MetaMind (acquired by Salesforce). As time permits, Darrell has served and is available as an expert witness for patent litigation relating to computer vision.