2 papers
stat.ML2025
Sinusoidal Approximation Theorem for Kolmogorov-Arnold Networks
Sergei Gleyzer, Hanh Nguyen, Dinesh P. Ramakrishnan +1
The Kolmogorov-Arnold representation theorem states that any continuous multivariable function can be exactly represented as a finite superposition of continuous single variable fu…
cs.LG2025
SineKAN: Kolmogorov-Arnold Networks Using Sinusoidal Activation Functions
Eric A. F. Reinhardt, P. R. Dinesh, Sergei Gleyzer
Recent work has established an alternative to traditional multi-layer perceptron neural networks in the form of Kolmogorov-Arnold Networks (KAN). The general KAN framework uses lea…