Metraipolis › archive › dc_023a166d68bf
Evaluating the Effectiveness of SechKAN on 1D Data — arXiv:2609.25876
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.25876
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T13:46:43.223Z
- SHA-256 of the archived text
25fad11b2ca8b6e91c5bf44ee2845ba4017f9d887b74461913ea9e94789e629d- Stable URL of this page
https://metraipolis.com/documento/dc_023a166d68bf
How to cite
Evaluating the Effectiveness of SechKAN on 1D Data — arXiv:2609.25876 — arXiv (en), https://arxiv.org/abs/2609.25876 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_023a166d68bf (Metraipolis archive dc_023a166d68bf, sha256 25fad11b2ca8b6e91c5bf44ee2845ba4017f9d887b74461913ea9e94789e629d)
BibTeX
@misc{dc023a166d68bf,
title = {Evaluating the Effectiveness of SechKAN on 1D Data — arXiv:2609.25876},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.25876},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_023a166d68bf; sha256 25fad11b2ca8b6e91c5bf44ee2845ba4017f9d887b74461913ea9e94789e629d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25876. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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: this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.25876 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T13:18:38.266Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).