I have implemented KAN using B-splines in a more efficient manner to enhance its performance. Additionally, I have thoroughly tested its performance on various datasets, including MNIST, Air Passengers, and CIFAR-10.

I will soon upload the results of all my experiments to provide a comprehensive overview of KAN's performance across different datasets.

Deep-KAN is a Python package for implementing Kolmogorov-Arnold-Networks (KAN). You can find the package here.

For 20 epochs with a single hidden layer(32 neurons) (Note: both are untuned)

You can find the RBF implementation of KAN here.