CORTEXA
← Browse
arxivcs.LGcs.AI2026-06-30

SechKAN: Kolmogorov-Arnold Networks with Hyperbolic Secant Functions

Hoang-Thang Ta

In recent years, Kolmogorov-Arnold Networks (KANs) have attracted increasing attention due to their effectiveness in machine learning and scientific computing tasks, offering a new paradigm for neural network design. In this paper, we present SechKAN, a KAN architecture based on hyperbolic secant (sech) functions. The hyperbolic secant basis is used for its smooth bell-shaped form, localized responses, and stable gradients. We employ 1D linear transformations to reduce the number of parameters, allowing SechKAN to remain comparable to multilayer perceptrons (MLPs) in model size. Experimental results indicate the effectiveness of SechKAN in function fitting, PDE problems, and image classification tasks on benchmark datasets, including MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100. SechKAN achieves superior performance compared to MLPs and other KAN variants while maintaining a similar number of parameters. However, its running time, while better than that of other KAN variants, is slightly longer than that of MLPs.

View free PDFSource page

Related papers

arxivcs.LGcs.AI2026-07-14

STKAN: Kolmogorov-Arnold Networks for Spatio-Temporal Forecasting

Sicong Lai, Yuehong Hu, Siru Zhong, Si Qiao, Yuxuan Liang, Guangyin Jin

Real-world traffic data exhibit heterogeneous spatial correlations and nonlinear temporal dynamics, posing substantial challenges for accurate spatio-temporal forecasting. Existing approaches have developed increasingly sophisticated graph, attention, and decomposition architectu…

View free PDFSource page
arxivcs.LGcs.AI2026-07-02

SA-HGNN: Sample-Adaptive Hyperbolic Graph Neural Network for EEG-Based Depression Recognition

Yang Li, Pan Hu, Yan Zhang, Wenfan Yang, Tao Wu, Lianbo Guo

Graph Neural Networks (GNNs) have been widely used to capture spatial functional connectivity patterns to improve electroencephalography (EEG)-based depression recognition performance. However, the functional connectivity of brain networks in patients with depression exhibits an…

View free PDFSource page
arxivcs.AIcs.LGcs.PL2026-07-18

Exact Network Surgery: Functional Invariance and Gradient Plasticity in Reactive Computational Graphs

Abdallah Khemais

Function-preserving network growth techniques such as Net2Net and progressive stacking expand a model's capacity without destroying its learned function, but existing formulations either tolerate numerical perturbations or require a full rebuild of the training program. We formal…

View free PDFSource page
arxivcs.LGcs.AIcs.ITeess.SP2026-07-20

Multi-layer MIMO Relay as Deep Physical Neural Networks: Power Amplifiers as Activation Functions

Meng Hua, Itsik Bergel, Deniz Gündüz

Wireless physical neural networks (WPNNs) embed neural computation directly into analog hardware, offering lower energy consumption and latency than conventional digital implementations. In this paper, we propose a deep WPNN in which nonlinear activations are realized by a multi-…

View free PDFSource page