KAN: Kolmogorov-Arnold Networks

arXiv:2404.19756v1 Announce Type: new
Abstract: Inspired by the Kolmogorov-Arnold representation theorem, we propose Kolmogorov-Arnold Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs). While MLPs have fixed activation functions on nodes ("neurons"), KANs have learnable activation functions on edges ("weights"). KANs have no linear weights at all -- every weight parameter is replaced by a univariate function parametrized as a spline. We show that this seemingly simple change makes KANs outperform MLPs in terms of accuracy and interpretability. For accuracy, …

abstract arxiv cond-mat.dis-nn cs.ai cs.lg every function functions layer linear networks neurons nodes representation stat.ml theorem type while