Show Menu


Haizhao Yang (Purdue University): A Few Thoughts on Deep Learning-Based PDE Solvers

Ort: MPI für Mathematik in den Naturwissenschaften Leipzig,  , Videobroadcast

Video broadcast: Math Machine Learning seminar MPI MIS + UCLA 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 PDE solvers. We present a few thoughts on the theoretical foundation of this topic for high-dimensional partial differential equations including approximation, optimization, and generalization. Though our analysis is not a complete story and there are many missing pieces to make it well-justified, it may still be helpful to provide some insights into deep learning.

No Attachment

Beginn: May 6, 2021, 5 p.m.

Ende: May 6, 2021, 6:30 p.m.