GistNoesis/FourierKAN

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

SineKAN: Kolmogorov-Arnold Networks Using Sinusoidal Activation Functions

Kolmogorov Arnold Networks

Implementation of "Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains" by Tancik et al.

This project is dedicated to the implementation and research of Kolmogorov-Arnold convolutional networks. The repository includes implementations of 1D, 2D, and 3D convolutions with different kernels, ResNet-like and DenseNet-like models, training code based on accelerate/PyTorch, as well as scripts for experiments with CIFAR-10 and Tiny ImageNet.

PyTorch implementation of the fractional Fourier transform with trainable transform order.

Parametric differentiable curves with PyTorch for continuous embeddings, shape-restricted models, or KANs

One library, four surfaces. Production-grade Kolmogorov-Arnold Networks || TensorFlow + PyTorch + ONNX. || A small KAN beats a 10× larger MLP on smooth, separable target. One library. Two backends. Real ONNX export. Docker + Kubernetes ready.

Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.