mlsanityData to 7 Oct 2026

Evaluating the Effectiveness of SechKAN on 1D Data

arXiv 2609.25876 ↗First posted 22 Sep 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The connection between the Kolmogorov-Arnold representation theorem (KART) and neural network design has led to the development of Kolmogorov-Arnold Networks (KANs), with applications ranging from STEM problems to AI tasks. In this paper, we investigate the effectiveness of a KAN variant, SechKAN, which relies on hyperbolic secant (sech) functions as basis functions, with a 1D projection to reduce the number of parameters to a level comparable to MLPs. We evaluate SechKAN on three 1D classification datasets: UCI Human Activity Recognition (UCI HAR), ElectricDevices, and Crop, and compare it with several effective networks, including EfficientKAN, MLP, CNN1D, ResNet1D, and DSCNN1D, using approximately comparable parameter budgets. The results indicate that SechKAN achieves competitive performance across the three datasets, with particularly strong performance on Crop. Ablation studies further show that grid size and normalization affect performance, suggesting that SechKAN's effectiveness depends on the dataset and architectural choices. Our source code and experimental implementation are publicly available at: https://github.com/hoangthangta/SechKAN_1D.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 28 references that are in the map. First posted on arXiv 22 Sep 2026.

Builds on

22 of 28 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2024KAN: Kolmogorov-Arnold Networkscited by 634
  3. 2024U-KAN Makes Strong Backbone for Medical Image Segmentation and Generationcited by 176
  4. 20191D Convolutional Neural Networks and Applications: A Surveycited by 152
  5. 2024Kolmogorov-Arnold Networks are Radial Basis Function Networkscited by 125
  6. 2024Wav-KAN: Wavelet Kolmogorov-Arnold Networkscited by 118
  7. 2024Chebyshev Polynomial-Based Kolmogorov-Arnold Networks: An Efficient Architecture for Nonlinear Function Approximationcited by 115
  8. 2024A Survey on Kolmogorov-Arnold Networkcited by 67
  9. 2024Kolmogorov Arnold Informed neural network: A physics-informed deep learning framework for solving forward and inverse problems based on Kolmogorov Arnold Networkscited by 64
  10. 2024fKAN: Fractional Kolmogorov-Arnold Networks with trainable Jacobi basis functionscited by 60
  11. 2024Kolmogorov-Arnold Transformercited by 56
  12. 2024A Temporal Kolmogorov-Arnold Transformer for Time Series Forecastingcited by 50
10 more
  1. 2024BSRBF-KAN: A combination of B-splines and Radial Basis Functions in Kolmogorov-Arnold Networkscited by 43
  2. 2020MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognitioncited by 36
  3. 2024ReLU-KAN: New Kolmogorov-Arnold Networks that Only Need Matrix Addition, Dot Multiplication, and ReLUcited by 32
  4. 2024rKAN: Rational Kolmogorov-Arnold Networkscited by 31
  5. 2025LeanKAN: A Parameter-Lean Kolmogorov-Arnold Network Layer with Improved Memory Efficiency and Convergence Behaviorcited by 12
  6. 2024Addressing common misinterpretations of KART and UAT in neural network literaturecited by 9
  7. 2025PRKAN: Parameter-Reduced Kolmogorov-Arnold Networkscited by 7
  8. 2022KASAM: Spline Additive Models for Function Approximationcited by 4
  9. 2025GS-KAN: Parameter-Efficient Kolmogorov-Arnold Networks via Sprecher-Type Shared Basis Functionscited by 3
  10. 2026SechKAN: Kolmogorov-Arnold Networks with Hyperbolic Secant Functionscited by 1

Built on by

Not cited yet.