Abstract: Deep learning methods have been a tremendously effective approach to problems in computer vision and natural language processing. However, these black-box models can be difﬁcult to deploy in practice as they are known to make unpredictable mistakes that can be hard to analyze and correct. In this talk, I will present collaborative research to develop visually interactive interfaces for probabilistic deep learning models, with the goal of allowing users to examine and correct black-box models through visualizations and interactive inputs. Through the co-design of models and visual interfaces, we will take the necessary next steps for model interpretability. Achieving this aim requires active investigation into developing new deep learning models and analysis techniques, and integrating them within interactive visualization frameworks.
Bio: Hanspeter Pfister is An Wang Professor of Computer Science in the School of Engineering and Applied Sciences at Harvard University. Before joining Harvard he worked for over a decade at Mitsubishi Electric Research Laboratories where he was Associate Director and Senior Research Scientist. He was the chief architect of VolumePro, Mitsubishi Electric's award-winning real-time volume rendering hardware for PCs. Dr. Pfister has a Ph.D. in Computer Science from the State University of New York at Stony Brook and an M.S. in Electrical Engineering from ETH Zurich, Switzerland. He is the recipient of the 2010 IEEE Visualization Technical Achievement award and the Petra T. Shattuck Excellence in Teaching Award in 2009. He is co-editor of the first textbook on Point-Based Computer Graphics, published by Elsevier in 2007, and was Technical Papers Chair for SIGGRAPH 2012.