Keras Efficient KAN
Project description
Keras Efficient Kan
Keras package reproducting the pytorch efficient_kan implementation
Package is available on pypi here
It implements KANLinear based on Kolmogorov-Arnold Network that can be used as a drop-in replacement for Dense layers in Keras models.
It supports array with more than 2 dimensions, applying the same transformation to all the dimensions except the last one.
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Close
Hashes for keras_efficient_kan-0.1.4.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | dfc62fdc799a138e6f2aa7f7920a9b2da6938d4ee8ff560ea0ad54ed31e00b56 |
|
MD5 | 4eafdd0e477cc07a7ddfed40901ea0e1 |
|
BLAKE2b-256 | d983e588e4b7215e23656c7bb30073de5c7e2ae134efe8cc4a22757fdec6bc2e |
Close
Hashes for keras_efficient_kan-0.1.4-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 61f4646c304516bfc40ad8004839a72eaa16874eb016c22a9400865736e01c19 |
|
MD5 | fa36600d77c714d56ce21ac0f918ba92 |
|
BLAKE2b-256 | 428df7eb959e3bc0dae99095edcb364fd3a5b17d5b5b0edd890afa870cd88f07 |