Development of an AI for poker, beginning with a foundation in distributed Proximal Policy Optimization (PPO) self-play mechanisms, and starting to integrate Counterfactual Regret Minimization (CRM) algorithms.
Code for the paper: Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions.
Code Package for the paper: Gaggle: Genetic Algorithms on the GPU using PyTorch.
Code for the paper 'On the Trade-Off Between Transparency and Security in Adversarial Machine Learning' accepted as an extended abstract at the AAMAS 2026 conference.
Code to produce the evaluation of the gaggle package, containing experiments for mnist_lenet, cartpole, and rastrigin.
RL for network dismantling attacks and defenses.
A complete chess engine and interactive game implemented entirely from scratch.
Self-correlation software implemented for the 2019 study 'Period Analysis of All-Sky Automated Survey for Supernovae (ASAS-SN) Data on Pulsating Red Giants'.