paper-with-me

홈 › Papers

LTBs-KAN: Linear-Time B-splines Kolmogorov-Arnold Networks

2026-04-23 · Eduardo Said Merin-Martinez, Andres Mendez-Vazquez, Eduardo Rodriguez-Tello arxiv

Kolmogorov-Arnold Networks (KANs) are a recent neural network architecture offering an alternative to Multilayer Perceptrons (MLPs) with improved explainability and expressibility. However, KANs are significantly slower than MLPs due to the recursive nature of B-spline function computations, limiting their application. This work addresses these issues by proposing a novel base-spline Linear-Time B-splines Kolmogorov-Arnold Network (LTBs-KAN) with linear complexity. Unlike previous methods that rely on the Boor-Mansfield-Cox spline algorithm or other computationally intensive mathematical functions, our approach significantly reduces the computational burden. Additionally, we further reduce model's parameter through product-of-sums matrix factorization in the forward pass without sacrificing performance. Experiments on MNIST, Fashion-MNIST and CIFAR-10 demonstrate that LTBs-KAN achieves good time complexity and parameter reduction, when used as building architectural blocks, compared to other KAN implementations.

📄 PDF Abstract BibTeX arXiv:2604.22034

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Kolmogorov-Arnold Networks are Radial Basis Function Networks

2024-05-10 · Ziyao Li

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 imple…

Kolmogorov-Arnold Networks

FC-KAN: Function Combinations in Kolmogorov-Arnold Networks

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

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 …

Image ClassificationKolmogorov-Arnold Networks

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

KAN-SAs: Efficient Acceleration of Kolmogorov-Arnold Networks on Systolic Arrays

2025-11-20 · Sohaib Errabii, Olivier Sentieys, Marcello Traiola arxiv

Kolmogorov-Arnold Networks (KANs) have garnered significant attention for their promise of improved parameter efficiency and explainability compared to traditional Deep Neural Networks (DNNs). KANs' key innovation lies i…

Input Convex Kolmogorov Arnold Networks

2025-05-27 · Thomas Deschatre, Xavier Warin

This article presents an input convex neural network architecture using Kolmogorov-Arnold networks (ICKAN). Two specific networks are presented: the first is based on a low-order, linear-by-part, representation of functi…

Kolmogorov-Arnold Networks