Kolmogorov-Arnold Newtworks (KANs)

This the github repo for the paper "KAN: Kolmogorov-Arnold Networks" [link]. The documentation can be found here [link].

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.

Installation

There are two ways to install pykan, through pypi or github.

Installation via github

git clone https://github.com/KindXiaoming/pykan.git
cd pykan
pip install -e .

Installation via pypi (soon)

pip install pykan

To install requirements:

pip install -r requirements.txt

Documentation

The documenation can be found here [].

Tutorials

Quickstart

Get started with hellokan.ipynb notebook

More demos

Jupyter Notebooks in docs/Examples and docs/API_demo are ready to play. You may also find these examples in documentation.