GitHub Pages.

Implementation of policy gradient for control in Ray + JAX

Fast Atari-style reinforcement learning environment.

Like https://github.com/kenjyoung/MinAtar but with no GUI

Basic bootstrap for NN experiments

For testing whether Bayesian NN priors are generalization-agnostic...or nah.

Code for upcoming TACL paper w/ Graham Neubig, "Neural Lattice Language Models".

Boilerplate code for quickly getting set up to run language modeling experiments

10-601 Machine Learning: Final Project. Tackled CIFAR classification in MatLab using neural nets, k-nearest neighbors, Gaussian Naive Bayes, SVMs, random forests, and more

11-711: Algorithms for NLP, HW4. Programming a shift-reduce dependency parser