Interpreting ML Models

This repo contains the projects for the course on Interpreting ML Models

It is a 4 week fast-paced hands-on course that covers a breadth of different interpretability approaches for deep learning models.

Each week focuses on a different data modality including vision, text, and tabular data. We also discuss evaluation metrics for interpretability methods and their tradeoffs in Week 3.

I am grateful to Praneeth for helping with the project content and adding the nice storyline to make each project super engaging and 10x more fun!

Here's the detailed syllabus for the course.