Abstract

Solving partial differential equations using neural networks  has received a lot of recent attention, due to its tremendous potential in the high-dimensional case. In this talk, I shall present our recent efforts for several class of boundary value problems that may contain singularities or non-self adjoint operators. I will present the numerical algorithms, discuss the convergence analysis issue, and illustrate the algorithms with numerical experiments.

Biography

Bangti Jin is a Chair Professor at the Chinese University of Hong Kong, and Global STEM scholar of Hong Kong SAR. His research interests include inverse problems, numerical analysis and machine learning. He was selected as a Highly Cited Researcher by Clarivate Analytics in 2022 and 2025, and received ICCM Silver Medal in Mathematics in 2025.