Saved in:
Bibliographic Details
Main Authors: Zhuang, Qiao, Wang, Taorui, Wanjiku, Rita, Bani-Yaghoub, Majid, Zhang, Zhongqiang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.02799
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913087299256320
author Zhuang, Qiao
Wang, Taorui
Wanjiku, Rita
Bani-Yaghoub, Majid
Zhang, Zhongqiang
author_facet Zhuang, Qiao
Wang, Taorui
Wanjiku, Rita
Bani-Yaghoub, Majid
Zhang, Zhongqiang
contents We extend our two-scale neural-network method for scalar singularly perturbed problems with one small parameter to dynamical systems with multiple small parameters. To accommodate multiple small parameters, we use a single effective scale parameter defined as the geometric mean of all parameters. We thus augment the network input with a scale-aware feature, enabling it to capture sharp solution transitions intrinsically. Numerical experiments across a range of dynamical systems demonstrate that the proposed framework can handle coupled systems with multiple and high-contrast small parameters and obtain satisfactory accuracy in capturing solution features induced by small parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2605_02799
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Two-scale Neural Networks for Singularly Perturbed Dynamical Systems with Multiple Parameters
Zhuang, Qiao
Wang, Taorui
Wanjiku, Rita
Bani-Yaghoub, Majid
Zhang, Zhongqiang
Numerical Analysis
Computational Physics
65N35, 34E15
I.2.6
We extend our two-scale neural-network method for scalar singularly perturbed problems with one small parameter to dynamical systems with multiple small parameters. To accommodate multiple small parameters, we use a single effective scale parameter defined as the geometric mean of all parameters. We thus augment the network input with a scale-aware feature, enabling it to capture sharp solution transitions intrinsically. Numerical experiments across a range of dynamical systems demonstrate that the proposed framework can handle coupled systems with multiple and high-contrast small parameters and obtain satisfactory accuracy in capturing solution features induced by small parameters.
title Two-scale Neural Networks for Singularly Perturbed Dynamical Systems with Multiple Parameters
topic Numerical Analysis
Computational Physics
65N35, 34E15
I.2.6
url https://arxiv.org/abs/2605.02799