References & Citations
Computer Science > Machine Learning
Title: Kolmogorov-Arnold Networks are Radial Basis Function Networks
(Submitted on 10 May 2024)
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.
Link back to: arXiv, form interface, contact.