This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN) to the Convolutional Layers, changing the classic linear transformation of the convolution to learnable non linear activations in each pixel.
MIT License
779
stars
76
forks
source link
How to calculate the number of KANConv parameters？ #19
Firstly, thanks to authors' KAN-CNN works.
A Convolutional KAN layer has K²(gridsize + 2) parameters, why does the KKAN model have a number of 94650 parameters?
Thanks.
Firstly, thanks to authors' KAN-CNN works. A Convolutional KAN layer has K²(gridsize + 2) parameters, why does the KKAN model have a number of 94650 parameters? Thanks.