The PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling

Implementation on how to use Kolmogorov-Arnold Networks (KANs) for classification and regression tasks.

Improved LBFGS and LBFGS-B optimizers in PyTorch.

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.

Testing KAN-based text generation GPT models

KAN meets Gram Polynomials

KANs for text classification on GLUE tasks

An implementation of the KAN architecture using learnable activation functions for knowledge distillation on the MNIST handwritten digits dataset. The project demonstrates distilling a three-layer teacher KAN model into a more compact two-layer student model, comparing the performance impacts of distillation versus non-distilled models.

This is the repo for the MixKABRN Neural Network (Mixture of Kolmogorov-Arnold Bit Retentive Networks), and an attempt at first adapting it for training on text, and later adjust it for other modalities.