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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ta, Hoang-Thang, Thai, Duy-Quy, Tran-Thi, Phuong-Linh
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916902483263488
author Ta, Hoang-Thang
Thai, Duy-Quy
Tran-Thi, Phuong-Linh
author_facet Ta, Hoang-Thang
Thai, Duy-Quy
Tran-Thi, Phuong-Linh
contents 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 (KANs) have attracted attention from the research community, stimulating the use of polynomial functions such as B-splines and RBFs. However, these functions are not fully supported by GPU devices and are still considered less popular. In this paper, we propose the use of fast computational functions, such as ReLU and trigonometric functions (e.g., ReLU, sin, cos, arctan), as basis components in Kolmogorov-Arnold Networks (KANs). By integrating these function combinations into the network structure, we aim to enhance computational efficiency. Experimental results show that these combinations maintain competitive performance while offering potential improvements in training time and generalization.
format Preprint
id arxiv_https___arxiv_org_abs_2508_11876
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Combinations of Fast Activation and Trigonometric Functions in Kolmogorov-Arnold Networks
Ta, Hoang-Thang
Thai, Duy-Quy
Tran-Thi, Phuong-Linh
Machine Learning
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 (KANs) have attracted attention from the research community, stimulating the use of polynomial functions such as B-splines and RBFs. However, these functions are not fully supported by GPU devices and are still considered less popular. In this paper, we propose the use of fast computational functions, such as ReLU and trigonometric functions (e.g., ReLU, sin, cos, arctan), as basis components in Kolmogorov-Arnold Networks (KANs). By integrating these function combinations into the network structure, we aim to enhance computational efficiency. Experimental results show that these combinations maintain competitive performance while offering potential improvements in training time and generalization.
title Combinations of Fast Activation and Trigonometric Functions in Kolmogorov-Arnold Networks
topic Machine Learning
url https://arxiv.org/abs/2508.11876