EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

On the Edge-Computing-Oriented Inference of Radial Basis Function-Based Kolmogorov–Arnold Networks

Georgios Venitourakis, Ioannis Koutoulas, Konstantina Sofia Charalampeli, Maria Eleni Patsi, Christoforos Kachris, Dionysios Reisis

Electronics · 06.06.2026 · 15 (12) · 2498

DOI: 10.3390/electronics15122498 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 06.06.2026. Verfasst von Georgios Venitourakis und 5 weiteren Autor:innen. Die Arbeit nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The emerging Kolmogorov–Arnold networks (KANs) have set a new standard in machine learning (ML) tasks by prevailing over traditionally deployed multilayer perceptrons (MLPs) thanks to their enhanced interpretability through activation function learning, while they require increased computational complexity and memory footprint. Radial-basis function (RBF)-based KAN models maintain high performance over other variants of KANs with considerable size reduction and consequently more efficient execution. Aiming at effectively supporting the inference of RBF-KANs on Internet-of-Things (IoT) devices, this paper focuses on edge-oriented computing and introduces a soft intellectual property (IP) core, written in hardware description language (HDL), targeting the execution of such networks on all-programmable systems-on-chip (APSoC). The proposed design is fully pipelined and runtime configurable, allowing for real-time inference and latency-sensitive neural network deployment on-the-fly. A testbench reveals up to 43.6× speedup when compared with a commercial edge central processing unit (CPU) and consumes considerably less power. The core’s adaptable design enables efficient allocation of resources and meets diverse throughput demands, making it well-suited for a broad range of IoT applications.

Zitieren

APA

Venitourakis, G., Koutoulas, I., Charalampeli, K. S., Patsi, M. E., Kachris, C., & Reisis, D. (2026). On the Edge-Computing-Oriented Inference of Radial Basis Function-Based Kolmogorov–Arnold Networks. Electronics, 15(12), 2498. https://doi.org/10.3390/electronics15122498

Vancouver

Venitourakis G, Koutoulas I, Charalampeli KS, Patsi ME, Kachris C, Reisis D. On the Edge-Computing-Oriented Inference of Radial Basis Function-Based Kolmogorov–Arnold Networks. Electronics. 2026;15(12):2498. doi:10.3390/electronics15122498

BibTeX
@article{Venitourakis2026,
  author = {Venitourakis, Georgios and Koutoulas, Ioannis and Charalampeli, Konstantina Sofia and Patsi, Maria Eleni and Kachris, Christoforos and Reisis, Dionysios},
  title = {On the Edge-Computing-Oriented Inference of Radial Basis Function-Based Kolmogorov–Arnold Networks},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {12},
  pages = {2498},
  doi = {10.3390/electronics15122498}
}
Kostenlos starten →