# code

Some open-source software that I maintain.

This Python package is a PyTorch framework for digging into the inner workings of hierarchical visual models (e.g. deep nets). I help build and maintain this repo with some friends in the lab. The part of the package to which I contribute most is synthesize/eigendistortion and its related code. It was a fun mix of machine learning and numerical linear algebra.

I’ve recommended the book Analyzing neural time series data by Mike Cohen to anyone I’ve met starting out in neural data analysis. In 2015, I set out to translate the book’s entire MATLAB codebase (thousands of lines) to Python in Jupyter notebooks , but abandoned it because it was quite frankly an insane use of my free time. Fast forward to 2021 – I learned that it had somehow accumulated 100+ stars and about 60+ forks on GitHub, so I figured why not finish what I started.

All code from blog posts will be pushed to this repo.