kolmogorov-arnold-representation

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

Kolmogorov–Arnold Networks (KAN) in PyTorch

Testing KAN-based text generation GPT models

Code for Kolmogorov-Arnold Network for Quantum Architecture Search i.e., KANQAS

NeuroBender, where the mystical powers of KAN network meet the robust stability of autoencoders!

Implementing KANs with TensorFlow

given beta-holder continuous function f:[0,1]^d -> R, this deep ReLU network approximates f up to approximation rate of 2^(-K beta) using 2^Kd parameters. Here, K is a set positive integer and d the dimension.

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 repository was created by Flatlogic Platform: https://flatlogic.com/generator | Application page: https://kan.flatlogic.app