发表机构
University of Information Technology; Vietnam National University Ho Chi Minh City（信息大学; 胡志明市越南国家大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文评估了基于双曲正割基函数和1D投影的SechKAN在三个一维分类数据集上的性能，与多种网络对比，结果显示其性能有竞争力，且受网格大小和归一化影响。
AI 中文摘要
Kolmogorov-Arnold表示定理（KART）与神经网络设计之间的联系催生了Kolmogorov-Arnold网络（KANs）的发展，其应用范围从STEM问题到AI任务。本文研究了一种KAN变体SechKAN的有效性，该变体采用双曲正割（sech）函数作为基函数，并通过一维投影将参数数量减少到与MLP相当的水平。我们在三个一维分类数据集上评估了SechKAN：UCI Human Activity Recognition（UCI HAR）、ElectricDevices和Crop，并将其与包括EfficientKAN、MLP、CNN1D、ResNet1D和DSCNN1D在内的几种有效网络进行了比较，使用了大致相当的参数预算。结果表明，SechKAN在三个数据集上均取得了有竞争力的性能，在Crop上表现尤为突出。消融研究进一步表明，网格大小和归一化会影响性能，这表明SechKAN的有效性取决于数据集和架构选择。我们的源代码和实验实现公开可获取，网址为：此https URL。
英文摘要
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.
Comments13 pages
