lgy112112/ikan

ikan: many kan variants for every body

45
/ 100
Emerging

This project offers various advanced Kolmogorov-Arnold Networks (KAN) that enhance traditional neural networks. It takes numerical datasets, like those from image recognition or financial markets, and processes them through optimized KAN models to produce more accurate and efficient predictions or classifications. It's intended for machine learning practitioners and researchers who build and experiment with neural network models.

304 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or practitioner looking to apply, compare, and optimize different Kolmogorov-Arnold Network (KAN) architectures for tasks like image classification or time-series prediction.

Not ideal if you are looking for a plug-and-play solution for general data analysis without deep engagement in neural network architecture customization.

machine-learning-research neural-network-design predictive-modeling image-classification time-series-analysis
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

304

Forks

39

Language

Python

License

MIT

Last pushed

Jul 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lgy112112/ikan"

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