Journal
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
Volume 374, Issue -, Pages -Publisher
ELSEVIER SCIENCE SA
DOI: 10.1016/j.cma.2020.113547
Keywords
Physics-informed learning; VPINNs; Variational neural network; Domain decomposition; Automatic differentiation; hp-refinement; Partial differential equations
Funding
- Applied Mathematics Program within the Department of Energy, USA on the PhILMs project [DE-SC0019453]
- DARPA CompMods program on the DeepMMnet project [HR00112090062]
Ask authors/readers for more resources
The study proposes a general framework for hp-variational physics-informed neural networks (hp-VPINNs) based on the nonlinear approximation of shallow and deep neural networks and hp-refinement via domain decomposition and projection onto high-order polynomials. The hp-refinement corresponds to a global approximation with a local learning algorithm for efficient network parameter optimization, demonstrating advantages in accuracy and training cost for function approximation and solving differential equations.
We formulate a general framework for hp-variational physics-informed neural networks (hp-VPINNs) based on the nonlinear approximation of shallow and deep neural networks and hp-refinement via domain decomposition and projection onto the space of high-order polynomials. The trial space is the space of neural network, which is defined globally over the entire computational domain, while the test space contains piecewise polynomials. Specifically in this study, the hp-refinement corresponds to a global approximation with a local learning algorithm that can efficiently localize the network parameter optimization. We demonstrate the advantages of hp-VPINNs in both accuracy and training cost for several numerical examples of function approximation and in solving differential equations. (C) 2020 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available