Xiliang Lv, Professor, Wuhan University

Tao Zhou, Professor

Numerical analysis of PINNs for the linear second order elliptic

10:00-11:00 June 10(Friday)

In recent years, physical informed neural networks (PINNs) have been shown to be a powerful tool for solving PDEs empirically. In this talk we provide some theoretical results related to the convergence rate to PINNs for the second order elliptic equations with Dirichlet boundary condition. The error estimations are decomposed into approximation error and statistical error, which depens on the number of training samples, depth and width of the deep neural networks.