报告人：蔡智强（大湾区大学）

报告时间：2026年10月22日（星期四）14:00-16:00

报告地点：科技楼南702会议室

报告摘要：Neural networks (NNs) have demonstrated remarkable performance in computer vision, natural language processing, and many other tasks of artificial intelligence. Recently, there has been a growing interest in leveraging NNs to solve partial differential equations (PDEs). Despite the rapid proliferation of articles in recent years, research on NN-based numerical methods for solving PDEs in the context of science and engineering is still in its early stages. Numerous critical open problems remain to be addressed before these methods can be broadly applied to solve computationally challenging problems. In this talk, I will first give a brief introduction of ReLU NNs from numerical analysis perspective. I will then discuss our works on addressing some of critical questions: exceptional approximation ability to singular functions, physics-preserving NN, efficient and reliable non-convex optimization, and adaptive design of NN architecture.

报告人简介：Zhiqiang Cai, Chair Professor, School of Sciences, Great Bay University.He received his Ph.D. in Mathematics from University of Colorado at Boulder. Prior to joining GBU in 2025, he was Professor of Mathematics at Purdue University. His research focuses on numerical solutions of partial differential equations, with applications in fluid and solid mechanics, electromagnetics, porous media flows, and machine learning for scientific computing.

邀请人：数学与统计学院