Kolmogorov-Arnold Networks are Radial Basis Function Networks

Ziyao Li
5/10/2024
cs.LGcs.AI

No official code found. Best implementation: ZiyaoLi/fast-kan (494 stars, Apache-2.0, last commit 2024-06-20).

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.

View on arXivView PDF

Code Implementations(1)

ZiyaoLi/fast-kanCommunity100%
Apache-2.0

FastKAN: Very Fast Implementation of Kolmogorov-Arnold Networks (KAN)

49465Python, Jupyter NotebookMay 9, 20242 years agoApache-2.0

Similar Papers

Free-RBF-KAN: Kolmogorov-Arnold Networks with Adaptive Radial Basis Functions for Efficient Function Learning

88% match2026

Combinations of Fast Activation and Trigonometric Functions in Kolmogorov-Arnold Networks

87% match2025

FC-KAN: Function Combinations in Kolmogorov-Arnold Networks

87% match2 repos392024

FC-KAN: Function Combinations in Kolmogorov-Arnold Networks

87% match2 repos392024

rKAN: Rational Kolmogorov-Arnold Networks

87% match1 repo222024

KAN/H: Kolmogorov-Arnold Network using Haar-like bases

86% match2025

Cite this paper

@article{li2024kolmogorovarnold,
  title  = {Kolmogorov-Arnold Networks are Radial Basis Function Networks},
  author = {Ziyao Li},
  year   = {2024},
  eprint = {2405.06721},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2405.06721v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2405.06721.svg)](https://codeofpaper.com/paper/2405.06721)

Discussion