2025年04月13日 星期日 登录 EN

学术活动
Residual-informed neural networks for partial differential equations
首页 - 学术活动
报告人:
Dan Hu, Professor, Shanghai Jiao Tong University
邀请人:
Haijun Yu, Professor
题目:
Residual-informed neural networks for partial differential equations
时间地点:
15:00-16:00 July 11 (Tuesday), Z301
摘要:

Deep learning has achieved wide success in solving Partial Differential Equations (PDEs), with particular strength in handling high dimensional problems and parametric problems. Nevertheless, there is still a lack of a clear picture on the designing of network architecture and the training of network parameters. In this work, we develop Residual-Informed Neural Networks (RINN) to solve partial differential equations. Compared to the widely used method PINN (Physics-Informed Neural Networks), RINN avoids calculating the high-order derivatives of neural networks, thus significantly reduces the computational cost.