catswe/LinearKAN

LinearKAN: A very fast implementation of Kolmogorov-Arnold Networks

32
/ 100
Emerging

This project offers a significantly faster way to train and use Kolmogorov-Arnold Networks (KANs) for machine learning tasks. It takes structured numerical data as input and produces processed numerical outputs, helping machine learning practitioners build and deploy models more efficiently. If you're working with AI models and need a powerful, yet accelerated alternative to traditional neural networks, this tool can help.

Use this if you are a machine learning engineer or researcher looking to leverage Kolmogorov-Arnold Networks (KANs) for their modeling capabilities but are hindered by their typical training and inference speed.

Not ideal if you are not working with machine learning models or specifically looking to implement Kolmogorov-Arnold Networks.

machine-learning deep-learning neural-networks model-training AI-acceleration
No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 15 / 25
Community 5 / 25

How are scores calculated?

Stars

20

Forks

1

Language

Python

License

Apache-2.0

Last pushed

Nov 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/catswe/LinearKAN"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.