An Improved Method for Physics-Informed Neural Networks That Accelerates Convergence
Physics-Informed Neural Networks (PINNs) have proven highly effective for solving high-dimensional Partial Differential Equations (PDEs), having demonstrated tremendous potential in a variety of challenging scenarios. However, traditional PINNs (vanilla PINNs), typically based on fully connected neu...
Main Authors: | Liangliang Yan, You Zhou, Huan Liu, Lingqi Liu |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2024-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10399482/ |
Similar Items
-
Weak convergence methods for nonlinear partial differential equations /
by: Evans, Lawrence C, et al.
Published: (1990) -
Dynamic & norm-based weights to normalize imbalance in back-propagated gradients of physics-informed neural networks
by: Shota Deguchi, et al.
Published: (2023-01-01) -
Strong μ‐faster convergence and strong μ‐acceleration of convergence by regular matrices
by: Ants Aasma
Published: (2008-03-01) -
On convergence of He’s variational iteration method for nonlinear partial differential equations
by: Jafar Saberi -Nadjafi, et al.
Published: (2013-01-01) -
A Second-Order Network Structure Based on Gradient-Enhanced Physics-Informed Neural Networks for Solving Parabolic Partial Differential Equations
by: Kuo Sun, et al.
Published: (2023-04-01)