Galerkin Neural Networks: A Framework for Approximating Variational Equations with Error Control

Abstract

We present a new approach to using neural networks to approximate the solutions of variational equations, based on the adaptive construction of a sequence of finite-dimensional subspaces whose basis functions are realizations of a sequence of neural networks. The finite-dimensional subspaces are then used to define a standard Galerkin approximation of the variational equation. This approach enjoys a number of advantages, including: the sequential nature of the algorithm offers a systematic approach to enhancing the accuracy of a given approximation; the sequential enhancements provide a useful indicator for the error that can be used as a criterion for terminating the sequential updates; the basic approach is largely oblivious to the nature of the partial differential equation under consideration; and, some basic theoretical results are presented regarding the convergence (or otherwise) of the method which are used to formulate basic guidelines for applying the method.

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• DGM: A deep learning algorithm for solving partial differential equations
• Solving high-dimensional partial differential equations using deep learning
• Adaptive activation functions accelerate convergence in deep and physics-informed neural networks
• A unified deep artificial neural network approach to partial differential equations in complex geometries
• Weak Adversarial Networks for High-dimensional Partial Differential Equations
• Variational Physics-Informed Neural Networks For Solving Partial Differential Equations
• Robust Training and Initialization of Deep Neural Networks: An Adaptive Basis Viewpoint

Cited by in corpus (2)

• Probabilistic partition of unity networks: clustering based deep approximation
• Machine-learning custom-made basis functions for partial differential equations