pranavgupta2603/kan-distillation

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.

Hi 👋, I'm Pranav Gupta

• 👯 I’m looking to collaborate on Deep Learning Projects.

• 💬 Researching on Diffusion Models, Image-Text representations

• 📫 How to reach me [email protected]

• ⚡ Fun fact I am from the future and I won the Turing Award

Connect with me:

Github Trophies:

Recent Blogs:

📊 GitHub Stats: