Kolmogorov-Arnold Networks
An interpretable neural network that helps scientists discover mathematical and physical laws
This is the github repo for the paper "KAN: Kolmogorov-Arnold Networks" and "KAN 2.0: Kolmogorov-Arnold Networks Meet Science". You may want to quickstart with hellokan, try more examples in tutorials, or read the documentation here.
Kolmogorov-Arnold Networks (KANs) are promising alternatives of Multi-Layer Perceptrons (MLPs). KANs have strong mathematical foundations just like MLPs: MLPs are based on the universal approximation theorem, while KANs are based on Kolmogorov-Arnold representation theorem. KANs and MLPs are dual: KANs have activation functions on edges, while MLPs have activation functions on nodes. This simple change makes KANs better (sometimes much better!) than MLPs in terms of both model accuracy and interpretability. A quick intro of KANs here.
