fkan: Fractional kolmogorov-arnold networks with trainable jacobi basis functions

AA Aghaei - Neurocomputing, 2025 - Elsevier
Recent advancements in neural network design have given rise to the development of
Kolmogorov-Arnold Networks (KANs), which enhance interpretability and precision of these …

An improved water strider algorithm for solving the inverse Burgers Huxley equation

HD Mazraeh, K Parand, M Hosseinzadeh, J Lansky… - Scientific Reports, 2024 - nature.com
In this paper, we introduce an improved water strider algorithm designed to solve the inverse
form of the Burgers-Huxley equation, a nonlinear partial differential equation. Additionally …

An innovative combination of deep Q-networks and context-free grammars for symbolic solutions to differential equations

HD Mazraeh, K Parand - Engineering Applications of Artificial Intelligence, 2025 - Elsevier
In this research paper, we propose a novel approach that combines deep Q-networks with
context-free grammars to solve differential equations symbolically. Our method utilizes the …

rKAN: Rational Kolmogorov-Arnold Networks

AA Aghaei - arxiv preprint arxiv:2406.14495, 2024 - arxiv.org
The development of Kolmogorov-Arnold networks (KANs) marks a significant shift from
traditional multi-layer perceptrons in deep learning. Initially, KANs employed B-spline curves …

Compact finite difference schemes and error estimation for third-order Emden-Fowler equations

N Sahoo, R Singh - Numerical Algorithms, 2025 - Springer
This manuscript presents a new higher-order numerical discretization scheme for solving
nonlinear third-order Emden-Fowler equations with local and nonlocal boundary conditions …