Latent Dynamics Discovery

John Langford
Partner Researcher Manager
Microsoft Research

Tuesday, August 8, 2023 | 11 AM
BA 1200

This lecture is open to the public.
No registration is required but space is limited.

Abstract:

When even small animals enter an environment, they can understand the environment well enough to orient, plan to traverse, and execute that plan effectively.  Although some engineered systems (e.g. SLAM for self-driving cars) have exhibited the same capability, the approaches tend to not be robust to sensor damage, augmentation, or adaptation.  This leads to a natural question: Can we systematically and robustly learn to develop the capability to orient, plane and execute in an environment?  The answer turns out to be “yes”.

Bio:

John Langford studied Physics and Computer Science at the California Institute of Technology, earning a double bachelor’s degree in 1997, and received his Ph.D. from Carnegie Mellon University in 2002. Since then, he has worked at Yahoo!, Toyota Technological Institute, and IBM‘s Watson Research Center. He is also the primary author of the popular Machine Learning weblog, hunch.net and the principle developer of Vowpal Wabbit. Previous research projects include Isomap, Captcha, Learning Reductions, Cover Trees, and Contextual Bandit learning.