Speaker:
Prof. Lu Lu，University of Pennsylvania
Inviter:
Title:
Physics-Informed Neural Network (PINN): Algorithms, Applications, and Software
Time & Venue:
2021.12.02 08:30–09:30 腾讯会议ID: 897 461 605
Abstract:
Deep learning has achieved remarkable success in diverse applications; however, its use in solving partial differential equations (PDEs) has emerged only recently. In this talk, I will first present an overview of physics-informed neural networks (PINNs), which embed a PDE into the loss of the neural network using automatic differentiation. I will also discuss several approaches to improve the efficiency and accuracy of PINN, including a residual-based adaptive refinement (RAR) method, gradient-enhanced PINN (gPINN), and PINN with hard constraints (hPINN). The PINN algorithm can also be applied to different types of PDEs, including integro-differential equations, fractional PDEs, and stochastic PDEs. Moreover, I will present a Python library for PINNs, DeepXDE.
--
FROM 202.121.181.*