Date: Monday, April 22, 2002
Time: 4:00 PM (talk telecast)
Place: Parks Shop, Studio 1, NCSU Historical Campus (click for courtesy parking request)
Speaker: Eric Horvitz , Microsoft Research
Uncertainty, Intelligence, and Interaction
Abstract: Nearly fifteen years ago, a renaissance in methods for representing and reasoning under uncertainty began to influence several subdisciplines of computer science. I will present research on harnessing explicit representations of probability and preference in software applications and services, with a focus on developments in human-computer interaction. I will review attempts to grapple with inescapable uncertainties in the knowledge, intentions, and attention of computer users. After highlighting key ideas, in the context of several representative projects at Microsoft Research, I will discuss longer-term research aimed at embedding representation, inference, and learning under uncertainty more deeply into the fabric of computer systems and interfaces.
Short Bio: Eric Horvitz is a senior researcher at Microsoft Research, where he manages the Adaptive Systems and Interaction group. His interests include principles of sensing, learning, and reasoning under uncertainty, and applications of probability and utility in computational problem solving, information retrieval, and human-computer interaction. He is the area editor of the Decisions, Uncertainty, and Computation Area of the Journal of the ACM, and currently serves on the Information Science and Technology (ISAT) Board of DARPA and on the Naval Research Advisory Committee (NRAC). He received Ph.D. and M.D. degrees from Stanford University.
Host: TBA , Computer Science, Duke
Colloquia Home Page.