Posts

Why start with documentation is bad advice, the loop I used instead, and the full story of my first merged pull request to Burn, the deep learning framework in Rust.

Taking the scalar autograd engine from the last post and making it hold matrices instead of single numbers, then watching it fall apart on MNIST until I fixed the weight init.

Building a small scalar autograd engine in Rust from scratch, then using it to train a tiny neural network. Based on Karpathy’s micrograd.

The first post: why I decided to start writing about what I learn and build.