A practitioner’s guide to Kolmogorov–Arnold networks

Kolmogorov–Arnold Networks (KANs), whose design is inspired—rather than dictated— by the Kolmogorov superposition theorem, have emerged as a structured alternative to MLPs. This review provides a systematic and comprehensive overview of the rapidly expanding KAN literature. The review is organized a...

Descripción completa

Detalles Bibliográficos
Autores: Noorizadegan Amir, Wang, Sifan, Ling, Leevan, Domínguez Morales, Juan Pedro
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2026
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:dnet:idus________::b18162e0adb9399fc1cae3e8ea2f8506
Acceso en línea:https://hdl.handle.net/11441/187131
https://doi.org/10.1016/j.cosrev.2026.100991
Access Level:acceso abierto
Palabra clave:Kolmogorov–arnold networks
Kolmogorov superposition theorem
Basis functions
Kernel methods
Neural network architectures
Physics-informed learning
Function approximation
Descripción
Sumario:Kolmogorov–Arnold Networks (KANs), whose design is inspired—rather than dictated— by the Kolmogorov superposition theorem, have emerged as a structured alternative to MLPs. This review provides a systematic and comprehensive overview of the rapidly expanding KAN literature. The review is organized around three core themes: (i) clarifying the relationships between KANs and Kolmogorov superposition theory (KST), MLPs, and classical kernel methods; (ii) analyzing basis functions as a central design axis; and (iii) summarizing recent advances in accuracy, efficiency, regularization, and convergence. Finally, we provide a practical “Choose–Your–KAN” guide and outline open research challenges and future directions. The accompanying GitHub repository (https://github.com/AmirNoori68/kan-review) serves as a structured reference for ongoing KAN research.