A Multi-Scale DNN Algorithm for Nonlinear Elliptic Equations with Multiple Scales

DOI10.4208/cicp.OA-2020-0187zbMath1474.65445arXiv2009.14597MaRDI QIDQ5162363

Xian Li, Lei Zhang, Zhi-Qin John Xu

Publication date: 2 November 2021

Published in: Communications in Computational Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2009.14597

zbMATH Keywords

variational formulation; \(p\)-Laplacian equation; activation function; deep neural network (DNN); multi-scale elliptic problem

Mathematics Subject Classification ID

68T07: Artificial neural networks and deep learning

65N30: Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs

41A46: Approximation by arbitrary nonlinear expressions; widths and entropy

35J66: Nonlinear boundary value problems for nonlinear elliptic equations

Uses Software

• DGM
• MscaleDNN