pykan icon indicating copy to clipboard operation
pykan copied to clipboard

Kolmogorov Arnold Networks

Results 336 pykan issues
Sort by recently updated
recently updated
newest added

After I trained the KAN on the dataset of mnist dataset. And fixed the symbolic formula. I got the symbolic formula from the model. Can I just use the symbolic...

I am trying to build a classifier using tensorflow dataset. How to load tf dataset into pykan for efficient computation time?

Now, I tried to train the KAN on a dataset that deals on classification. My question are these: ![image](https://github.com/KindXiaoming/pykan/assets/56232734/1f3319e6-91ba-4564-ab44-0afa64e7cb26) ![image](https://github.com/KindXiaoming/pykan/assets/56232734/f4ff7f35-5fb9-4281-b9db-665e43007297) ![image](https://github.com/KindXiaoming/pykan/assets/56232734/4ef98a02-c05f-4de8-a624-9366b79cba2a) ![image](https://github.com/KindXiaoming/pykan/assets/56232734/bda151cc-6245-4b91-b960-9297fdfc6c89) ![image](https://github.com/KindXiaoming/pykan/assets/56232734/80a68845-acd5-4926-870b-38625f487ed4) Now when I tried to run this:...

I want to store model parameters as weights and bias files for each layer (along with function names etc), how to do it?

train loss: 5.15e-01 | test loss: 5.33e-01 | reg: 1.47e+01 : 44%|▍| 436/1000 [04:19

While training KAN using entire samples say 10000, end up in memory overflow issue. Instead of giving entire data at once on "dataset" dict, can we train KAN on small...

Could anyone remind me how to prove the Theorem 2.1? I can hardly understand the effect on the superscript G on functions, \Phi_j. Moreover, the notation of C^m norm seems...