Notes on machine learning, experiments, and sports analytics.
A from-scratch walkthrough of the Vision Transformer architecture in a notebook.
A readable, from-scratch GPT-style Transformer in PyTorch — embeddings, causal attention, multi-head, MLP, residual blocks, training and generation.
Using a pre-trained classifier to classify bears into ‘Teddy’, ‘Black’, and ‘Grizzly’ bears.
