Simon-Bertrand/KAN-PyTorch

Kolmogorov–Arnold Networks (KAN) in PyTorch

33
/ 100
Emerging

This is a specialized tool for machine learning researchers and practitioners who are experimenting with novel neural network architectures. It allows you to build models using Kolmogorov-Arnold Networks (KANs), which are an alternative to traditional Multi-Layer Perceptrons (MLPs). You input your dataset and get a KAN-based model that can be trained for tasks like classification.

No commits in the last 6 months.

Use this if you are exploring advanced neural network architectures beyond standard MLPs and are interested in the properties and performance of Kolmogorov-Arnold Networks for your machine learning tasks.

Not ideal if you need a fully-featured, production-ready KAN implementation with automatic pruning or symbolic capabilities, or if you are not comfortable working with experimental deep learning models.

deep-learning-research neural-network-design machine-learning-experimentation model-architecture scientific-machine-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

25

Forks

3

Language

Python

License

GPL-3.0

Last pushed

May 05, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Simon-Bertrand/KAN-PyTorch"

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