ImpersonateGPT
Generative language models fine-tuned on the works of Dostoevsky, Fitzgerald, and Twain to capture their distinctive writing styles.
I'm an ML engineer who likes building things and understanding why they work. This site is a collection of projects I've built to feed that curiosity. Some to sharpen my understanding of a topic, others just because they sounded fun to make.
I studied math at Northwestern and computational math at Stanford. After a few years working in San Francisco, I moved to Paris to learn French and experience life in Europe. I'm now back home in Texas after more than a decade away.
Outside of work, I like hiking, cooking, playing tennis, and getting my heart broken by the underperformance of Texas A&M football.
Generative language models fine-tuned on the works of Dostoevsky, Fitzgerald, and Twain to capture their distinctive writing styles.
My attempt at re-creating Google Translate. An English-to-French neural machine translation model that uses an encoder-decoder transformer built from scratch in PyTorch.
Custom method for ranking college football teams inspired by Googleβs PageRank algorithm.
Simple RAG system that answers questions about US presidents based on their Wikipedia articles.
Convex optimization solver built from scratch using only primitive linear algebra operations.
Web app that extracts Sudoku puzzles from uploaded photos and solves them with a backtracking algorithm.
Toy app to visualize Bayesian Optimization in 1D.