rKAN: Rational Kolmogorov-Arnold networks.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 41930548.
- Also identified by DOI 10.1016/j.neunet.2026.108888.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
The development of Kolmogorov-Arnold networks (KANs) marks a significant shift from traditional multi-layer perceptrons in deep learning. Initially, KANs employed learnable B-spline curves as their primary basis function, but their inherent complexity posed implementation challenges. Consequently, researchers have explored alternative basis functions such as wavelets, polynomials, and fractional functions. This paper explores the use of rational functions as a novel basis function for KANs. Two different approaches based on Padé approximation and rational Jacobi functions as trainable basis functions are proposed to define the rational KAN (rKAN). The rKAN's performance has been evaluated across various domains, including deep learning and physics-informed deep learning, where it demonstrates its superiority in comparison to its alternatives with 99.29% accuracy on MNIST classification, 86.6% accuracy in text sentiment analysis, and a solution to the CartPole reinforcement learning task in approximately 200 episodes.