English

Deep neural network for solving differential equations motivated by Legendre-Galerkin approximation

Numerical Analysis 2020-10-27 v1 Machine Learning Numerical Analysis

Abstract

Nonlinear differential equations are challenging to solve numerically and are important to understanding the dynamics of many physical systems. Deep neural networks have been applied to help alleviate the computational cost that is associated with solving these systems. We explore the performance and accuracy of various neural architectures on both linear and nonlinear differential equations by creating accurate training sets with the spectral element method. Next, we implement a novel Legendre-Galerkin Deep Neural Network (LGNet) algorithm to predict solutions to differential equations. By constructing a set of a linear combination of the Legendre basis, we predict the corresponding coefficients, αi\alpha_i which successfully approximate the solution as a sum of smooth basis functions ui=0Nαiφiu \simeq \sum_{i=0}^{N} \alpha_i \varphi_i. As a computational example, linear and nonlinear models with Dirichlet or Neumann boundary conditions are considered.

Keywords

Cite

@article{arxiv.2010.12975,
  title  = {Deep neural network for solving differential equations motivated by Legendre-Galerkin approximation},
  author = {Bryce Chudomelka and Youngjoon Hong and Hyunwoo Kim and Jinyoung Park},
  journal= {arXiv preprint arXiv:2010.12975},
  year   = {2020}
}

Comments

19 pages, 7 figures, 1 table

R2 v1 2026-06-23T19:37:17.706Z