Finite basis Kolmogorov-Arnold networks: domain decomposition for data-driven and physics-informed problems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Howard, Amanda A., Jacob, Bruno, Helfert, Sarah, Heinlein, Alexander, Stinis, Panos
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909902705786880
author Howard, Amanda A.
Jacob, Bruno
Helfert, Sarah
Heinlein, Alexander
Stinis, Panos
author_facet Howard, Amanda A.
Jacob, Bruno
Helfert, Sarah
Heinlein, Alexander
Stinis, Panos
contents Kolmogorov-Arnold networks (KANs) have attracted attention recently as an alternative to multilayer perceptrons (MLPs) for scientific machine learning. However, KANs can be expensive to train, even for relatively small networks. Inspired by finite basis physics-informed neural networks (FBPINNs), in this work, we develop a domain decomposition method for KANs that allows for several small KANs to be trained in parallel to give accurate solutions for multiscale problems. We show that finite basis KANs (FBKANs) can provide accurate results with noisy data and for physics-informed training.
format Preprint
id arxiv_https___arxiv_org_abs_2406_19662
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Finite basis Kolmogorov-Arnold networks: domain decomposition for data-driven and physics-informed problems
Howard, Amanda A.
Jacob, Bruno
Helfert, Sarah
Heinlein, Alexander
Stinis, Panos
Machine Learning
Computational Physics
Kolmogorov-Arnold networks (KANs) have attracted attention recently as an alternative to multilayer perceptrons (MLPs) for scientific machine learning. However, KANs can be expensive to train, even for relatively small networks. Inspired by finite basis physics-informed neural networks (FBPINNs), in this work, we develop a domain decomposition method for KANs that allows for several small KANs to be trained in parallel to give accurate solutions for multiscale problems. We show that finite basis KANs (FBKANs) can provide accurate results with noisy data and for physics-informed training.
title Finite basis Kolmogorov-Arnold networks: domain decomposition for data-driven and physics-informed problems
topic Machine Learning
Computational Physics
url https://arxiv.org/abs/2406.19662