paper-with-me

홈 › Papers

FC-KAN: Function Combinations in Kolmogorov-Arnold Networks

2024-09-03 · Hoang-Thang Ta, Duy-Quy Thai, Abu Bakar Siddiqur Rahman, Grigori Sidorov, Alexander Gelbukh

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, representations of quadratic and cubic functions, concatenation, linear transformation of the concatenated output, and others. In our experiments, we compare FC-KAN with a multi-layer perceptron network (MLP) and other existing KANs, such as BSRBF-KAN, EfficientKAN, FastKAN, and FasterKAN, on the MNIST and Fashion-MNIST datasets. Two variants of FC-KAN, which use a combination of outputs from B-splines and Difference of Gaussians (DoG) and from B-splines and linear transformations in the form of a quadratic function, outperformed overall 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.

📄 PDF Abstract BibTeX arXiv:2409.01763

Code (2)

hoangthangta/fc_kan 공식 구현 pytorch
hoangthangta/all-kan pytorch

Tasks

Image ClassificationKolmogorov-Arnold Networks

Similar Papers 제목 키워드 기반

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

2025-08-16 · Hoang-Thang Ta, Duy-Quy Thai, Phuong-Linh Tran-Thi arxiv

For years, many neural networks have been developed based on the Kolmogorov-Arnold Representation Theorem (KART), which was created to address Hilbert's 13th problem. Recently, relying on KART, Kolmogorov-Arnold Networks…

Computational Efficiency

Function Fitting Based on Kolmogorov-Arnold Theorem and Kernel Functions

2025-03-29 · Jianpeng Liu, Qizhi Pan

This paper proposes a unified theoretical framework based on the Kolmogorov-Arnold representation theorem and kernel methods. By analyzing the mathematical relationship among kernels, B-spline basis functions in Kolmogor…

Kolmogorov-Arnold Networks

KKANs: Kurkova-Kolmogorov-Arnold Networks and Their Learning Dynamics

2024-12-21 · Juan Diego Toscano, Li-Lian Wang, George Em Karniadakis

Inspired by the Kolmogorov-Arnold representation theorem and Kurkova's principle of using approximate representations, we propose the Kurkova-Kolmogorov-Arnold Network (KKAN), a new two-block architecture that combines r…

Kolmogorov-Arnold NetworksOperator learningPhysics-informed machine learning

AF-KAN: Activation Function-Based Kolmogorov-Arnold Networks for Efficient Representation Learning

2025-03-08 · Hoang-Thang Ta, Anh Tran

Kolmogorov-Arnold Networks (KANs) have inspired numerous works exploring their applications across a wide range of scientific problems, with the potential to replace Multilayer Perceptrons (MLPs). While many KANs are des…

image-classificationImage ClassificationKolmogorov-Arnold NetworksRepresentation Learning

BSRBF-KAN: A combination of B-splines and Radial Basis Functions in Kolmogorov-Arnold Networks

2024-06-17 · Hoang-Thang Ta

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-l…

Image ClassificationKolmogorov-Arnold Networks