Home / Papers / Kolmogorov-Arnold Networks are Radial Basis Function Networks

Kolmogorov-Arnold Networks are Radial Basis Function Networks

DOI: 10.48550/arXiv.2405.06721Semantic Scholar

36 Citations•2024•

Ziyao Li

ArXiv

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 leads to FastKAN, a much faster implementation of KAN which is also a radial basis function (RBF) network.

Abstract

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.