Kolmogorov-Arnold Networks are Radial Basis Function Networks

Ziyao Li

Kolmogorov-Arnold Networks are Radial Basis Function Networks

Machine Learning 2024-05-14 v1 Artificial Intelligence

Authors: Ziyao Li

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.

Keywords

kolmogorov-arnold network

Cite

@article{arxiv.2405.06721,
  title  = {Kolmogorov-Arnold Networks are Radial Basis Function Networks},
  author = {Ziyao Li},
  journal= {arXiv preprint arXiv:2405.06721},
  year   = {2024}
}

Related papers

View all related →