Home Contact Links Jobs
Introduction Admissions Programs People Research Community Outreach News & Seminars
Differentiate Everything: A Lesson from Deep Learning
Speaker Prof. Lei Wang, Institute of Physics, Chinese Academy of Sciences
Date 24 November 2020 (Tuesday)
Time 12:30 - 14:00
Venue Zoom Meeting ID: 981 0617 3849 (Passcode: 944788)

Deep learning taught us a new way to play with computers: compose differentiable components into a computer program, then tune its parameters via gradient optimization until that program achieves what we want. This is the key idea of differentiable programming. The rapid development of deep learning technology offers convenient tools for differentiable programming, and also opens a new frontier for computational physics. I will introduce the basic notion of differentiable programming, and its physics applications including modeling, optimization, control, and inverse design.