Improved randomized neural network methods with boundary processing for solving elliptic equations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Huifang, Sheng, Zhiqiang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916337186504704
author Zhou, Huifang
Sheng, Zhiqiang
author_facet Zhou, Huifang
Sheng, Zhiqiang
contents We present two improved randomized neural network methods, namely RNN-Scaling and RNN-Boundary-Processing (RNN-BP) methods, for solving elliptic equations such as the Poisson equation and the biharmonic equation. The RNN-Scaling method modifies the optimization objective by increasing the weight of boundary equations, resulting in a more accurate approximation. We propose the boundary processing techniques on the rectangular domain that enforce the RNN method to satisfy the non-homogeneous Dirichlet and clamped boundary conditions exactly. We further prove that the RNN-BP method is exact for some solutions with specific forms and validate it numerically. Numerical experiments demonstrate that the RNN-BP method is the most accurate among the three methods, the error is reduced by 6 orders of magnitude for some tests.
format Preprint
id arxiv_https___arxiv_org_abs_2407_18457
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improved randomized neural network methods with boundary processing for solving elliptic equations
Zhou, Huifang
Sheng, Zhiqiang
Numerical Analysis
We present two improved randomized neural network methods, namely RNN-Scaling and RNN-Boundary-Processing (RNN-BP) methods, for solving elliptic equations such as the Poisson equation and the biharmonic equation. The RNN-Scaling method modifies the optimization objective by increasing the weight of boundary equations, resulting in a more accurate approximation. We propose the boundary processing techniques on the rectangular domain that enforce the RNN method to satisfy the non-homogeneous Dirichlet and clamped boundary conditions exactly. We further prove that the RNN-BP method is exact for some solutions with specific forms and validate it numerically. Numerical experiments demonstrate that the RNN-BP method is the most accurate among the three methods, the error is reduced by 6 orders of magnitude for some tests.
title Improved randomized neural network methods with boundary processing for solving elliptic equations
topic Numerical Analysis
url https://arxiv.org/abs/2407.18457