Repository Details
Shared by
HelloGitHub Rating
0 ratings
A Brand-New Neural Network Architecture
Past 7 days Received 2 stars ✨
Use arrow keys to explore dates, Home and End for the first and last date, Escape to dismiss.| Date | Star | Daily change |
|---|---|---|
| 周二 | 16,343 | — |
| 周三 | 16,345 | +2 |
| 周四 | 16,345 | 0 |
| 周五 | 16,345 | 0 |
| 周六 | 16,346 | +1 |
| 周日 | 16,345 | -1 |
| 周一 | 16,345 | 0 |
16.3k
Stars
No
Chinese
Jupyter Notebook
Language
No
Active
26
Contributors
266
Issues
No
Organization
None
Latest
2k
Forks
MIT
License

Inspired by the Kolmogorov-Arnold representation theorem, this project applies it to the design of neural networks. The main difference between KAN (Kolmogorov-Arnold Network) and the traditional Multilayer Perceptron (MLP) architecture is the application of activation functions. In KAN, activation functions are placed on the weights, resulting in a potentially more accurate and interpretable, albeit sometimes slower to train, network than the MLP.
Comments
Rating:
No comments yet