LeanKAN: a parameter-lean Kolmogorov-Arnold network layer with improved memory efficiency and convergence behavior
- 19 July 2025
- journal article
- Published by Elsevier in Neural Networks
- Vol. 192, 107883
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- National Science Foundation (CBET-2143625)
- National Science Foundation Graduate Research Fellowship Program (1745302)
This publication has 14 references indexed in Scilit:
- DeepOKAN: Deep operator network based on Kolmogorov Arnold networks for mechanics problemsComputer Methods in Applied Mechanics and Engineering, 2025
- Kolmogorov–Arnold-Informed neural network: A physics-informed deep learning framework for solving forward and inverse problems based on Kolmogorov–Arnold NetworksComputer Methods in Applied Mechanics and Engineering, 2024
- KAN-ODEs: Kolmogorov–Arnold network ordinary differential equations for learning dynamical systems and hidden physicsComputer Methods in Applied Mechanics and Engineering, 2024
- On the Kolmogorov neural networksNeural Networks, 2024
- The Kolmogorov–Arnold representation theorem revisitedNeural Networks, 2021
- A deep machine learning algorithm for construction of the Kolmogorov–Arnold representationEngineering Applications of Artificial Intelligence, 2021
- Runge–Kutta pairs of order 5(4) satisfying only the first column simplifying assumptionComputers & Mathematics with Applications, 2011
- On Kolmogorov's representation of functions of several variables by functions of one variableJournal of Econometrics, 2004
- Kolmogorov's spline networkIEEE Transactions on Neural Networks, 2003
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989