Kolmogorov-Arnold Networks are Radial Basis Function Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Li, Ziyao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911873181417472
author Li, Ziyao
author_facet Li, Ziyao
contents This short paper is a fast proof-of-concept that the 3-order B-splines used in Kolmogorov-Arnold Networks (KANs) can be well approximated by Gaussian radial basis functions. Doing so leads to FastKAN, a much faster implementation of KAN which is also a radial basis function (RBF) network.
format Preprint
id arxiv_https___arxiv_org_abs_2405_06721
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Kolmogorov-Arnold Networks are Radial Basis Function Networks
Li, Ziyao
Machine Learning
Artificial Intelligence
This short paper is a fast proof-of-concept that the 3-order B-splines used in Kolmogorov-Arnold Networks (KANs) can be well approximated by Gaussian radial basis functions. Doing so leads to FastKAN, a much faster implementation of KAN which is also a radial basis function (RBF) network.
title Kolmogorov-Arnold Networks are Radial Basis Function Networks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2405.06721