arXiv Analytics

Sign in

arXiv:2409.01763 [cs.LG]AbstractReferencesReviewsResources

FC-KAN: Function Combinations in Kolmogorov-Arnold Networks

Hoang-Thang Ta, Duy-Quy Thai, Abu Bakar Siddiqur Rahman, Grigori Sidorov, Alexander Gelbukh

Published 2024-09-03, updated 2024-10-14Version 2

In this paper, we introduce FC-KAN, a Kolmogorov-Arnold Network (KAN) that leverages combinations of popular mathematical functions such as B-splines, wavelets, and radial basis functions on low-dimensional data through element-wise operations. We explore several methods for combining the outputs of these functions, including sum, element-wise product, the addition of sum and element-wise product, quadratic function representation, and concatenation. In our experiments, we compare FC-KAN with multi-layer perceptron network (MLP) and other existing KANs, such as BSRBF-KAN, EfficientKAN, FastKAN, and FasterKAN, on the MNIST and Fashion-MNIST datasets. A variant of FC-KAN, which uses a combination of outputs from B-splines and Difference of Gaussians (DoG) in the form of a quadratic function, outperformed all other models on the average of 5 independent training runs. We expect that FC-KAN can leverage function combinations to design future KANs. Our repository is publicly available at: https://github.com/hoangthangta/FC_KAN.

Related articles: Most relevant | Search more
arXiv:2408.04841 [cs.LG] (Published 2024-08-09)
Kolmogorov-Arnold Network for Online Reinforcement Learning
arXiv:2409.08806 [cs.LG] (Published 2024-09-13)
TabKANet: Tabular Data Modelling with Kolmogorov-Arnold Network and Transformer
arXiv:2411.06078 [cs.LG] (Published 2024-11-09)
A Survey on Kolmogorov-Arnold Network