Lee

To use KANs in other datasets, you can use the KAN model like a layer. The forward method is defined within the KAN module, so you can pass the input...

The sigmoid can be used. Since the KAN module provides a foward method, using it like the old nn.Linear() didn't cause too many problems. " from kan import KAN from...

Have you tried lowering the grid number to 3 or less, I had a similar issue with another issue and it improved somewhat when I lowered the grid to 2.

  If we infer a function such as e^(x^2+1), we divide the sequence into two parts and construct a KAN with two weight layers, x^2 + 1 and exp....

I'm sorry, I don't have the math knowledge to answer that question, but when I trained the function I presented above, I left the last 20% x (i.e. x corresponding...

 This is the result of using this part as training data and  the rest of this photo as validation data. And when I trained like that, I changed...

We have found that increasing the layer while decreasing the grid improves this behavior. In the picture above, you can see that the overfitting is significantly improved when grid=2. However,...

Sounds like a great idea!! Do you have a page that you've researched or written code for?

Ok. Thank you for great idea