A Few Thoughts on Deep Learning-Based Scientific Computing

Series
Applied and Computational Mathematics Seminar
Time
Monday, October 26, 2020 - 2:00pm for 1 hour (actually 50 minutes)
Location
https://bluejeans.com/884917410
Speaker
Haizhao Yang – Purdue University – yang1863@purdue.eduhttps://haizhaoyang.github.io/
Organizer
Wenjing Liao

The remarkable success of deep learning in computer science has evinced potentially great applications of deep learning in computational and applied mathematics. Understanding the mathematical principles of deep learning is crucial to validating and advancing deep learning-based scientific computing. We present a few thoughts on the theoretical foundation of this topic and our methodology for designing efficient solutions of high-dimensional and highly nonlinear partial differential equations, mainly focusing on the approximation and optimization of deep neural networks.