paper-with-me

Papers

LArctan-SKAN: Simple and Efficient Single-Parameterized Kolmogorov-Arnold Networks using Learnable Trigonometric Function

2024-10-25 · Zhijie Chen, Xinglin Zhang

This paper proposes a novel approach for designing Single-Parameterized Kolmogorov-Arnold Networks (SKAN) by utilizing a Single-Parameterized Function (SFunc) constructed from trigonometric functions. Three new SKAN variants are developed: LSin-SKAN, LCos-SKAN, and LArctan-SKAN. Experimental validation on the MNIST dataset demonstrates that LArctan-SKAN excels in both accuracy and computational efficiency. Specifically, LArctan-SKAN significantly improves test set accuracy over existing models, outperforming all pure KAN variants compared, including FourierKAN, LSS-SKAN, and Spl-KAN. It also surpasses mixed MLP-based models such as MLP+rKAN and MLP+fKAN in accuracy. Furthermore, LArctan-SKAN exhibits remarkable computational efficiency, with a training speed increase of 535.01% and 49.55% compared to MLP+rKAN and MLP+fKAN, respectively. These results confirm the effectiveness and potential of SKANs constructed with trigonometric functions. The experiment code is available at https://github.com/chikkkit/LArctan-SKAN .

📄 PDF Abstract BibTeX arXiv:2410.19360

Code (1)

chikkkit/larctan-skan 공식 구현 pytorch

Tasks

Computational EfficiencyKolmogorov-Arnold Networks

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
+ ( 1 ) ⟷ 805 ⟷ ( 330 ) ⟷ 4056|How do I file a complaint with Expedia? How do I file a complaint with Expedia contact customer service at + ( 1 ) ⟷ 888 ⟷ ( 829 ) ⟷ 0881 or + ( 1 ) ⟷ 805 ⟷ ( 330 ) ⟷ 4056, or use their Help Center. Explain your issue…
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

LSS-SKAN: Efficient Kolmogorov-Arnold Networks based on Single-Parameterized Function

2024-10-19 · Zhijie Chen, Xinglin Zhang

The recently proposed Kolmogorov-Arnold Networks (KAN) networks have attracted increasing attention due to their advantage of high visualizability compared to MLP. In this paper, based on a series of small-scale experime…

Kolmogorov-Arnold Networks

asKAN: Active Subspace embedded Kolmogorov-Arnold Network

2025-04-07 · Zhiteng Zhou, Zhaoyue Xu, Yi Liu, Shizhao Wang

The Kolmogorov-Arnold Network (KAN) has emerged as a promising neural network architecture for small-scale AI+Science applications. However, it suffers from inflexibility in modeling ridge functions, which is widely used…

TSKANMixer: Kolmogorov-Arnold Networks with MLP-Mixer Model for Time Series Forecasting

2025-02-25 · Young-Chae Hong, Bei Xiao, Yangho Chen

Time series forecasting has long been a focus of research across diverse fields, including economics, energy, healthcare, and traffic management. Recent works have introduced innovative architectures for time series mode…

Kolmogorov-Arnold NetworksManagementTime SeriesTime Series Forecasting

Hierarchical RBF-KAN and RBF-SKAN Architectures for Multidimensional Function Approximation and Random Field Learning

2026-06-01 · Mingtao Xia, Qijing Shen arxiv

In this manuscript, we propose and analyze hierarchical Kolmogorov--Arnold neural network architectures employing radial basis functions as activation functions for approximating deterministic functions and random field …

Racing to Learn: Statistical Inference and Learning in a Single Spiking Neuron with Adaptive Kernels

2014-08-06 · Saeed Afshar, Libin George, Jonathan Tapson, Andre van Schaik 외

This paper describes the Synapto-dendritic Kernel Adapting Neuron (SKAN), a simple spiking neuron model that performs statistical inference and unsupervised learning of spatiotemporal spike patterns. SKAN is the first pr…