BSRBF-KAN: A combination of B-splines and Radial Basis Functions in Kolmogorov-Arnold Networks
This work addresses the need for more effective KAN architectures in machine learning, though it appears incremental as it builds on existing KAN methods by combining known mathematical functions.
The paper tackles the problem of designing Kolmogorov-Arnold Networks (KANs) by introducing BSRBF-KAN, which combines B-splines and radial basis functions, achieving competitive average accuracies of 97.55% on MNIST and 89.33% on Fashion-MNIST with stable convergence.
In this paper, we introduce BSRBF-KAN, a Kolmogorov Arnold Network (KAN) that combines B-splines and radial basis functions (RBFs) to fit input vectors during data training. We perform experiments with BSRBF-KAN, multi-layer perception (MLP), and other popular KANs, including EfficientKAN, FastKAN, FasterKAN, and GottliebKAN over the MNIST and Fashion-MNIST datasets. BSRBF-KAN shows stability in 5 training runs with a competitive average accuracy of 97.55% on MNIST and 89.33% on Fashion-MNIST and obtains convergence better than other networks. We expect BSRBF-KAN to open many combinations of mathematical functions to design KANs. Our repo is publicly available at: https://github.com/hoangthangta/BSRBF_KAN.