Notebooks developed in Mathematica for my Ph.D. thesis and other resources

Production-ready framework for training robust computer vision models. Features multi-GPU support, EMA tracking, label smoothing, and comprehensive robustness evaluation across 4 noise types. Includes scalable TF.Data pipeline, automated testing, Docker support, and CLI tools. Install: pip install robust-vision

MPGD: Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent

Research Project on NMF

A research-driven analysis of dynamic ticket pricing, modeling distributions with scaled Beta estimates derived from limited statistics (min, max, mean, median). The approach enriches Random Forest classification by incorporating shape parameters (α, β) and leveraging constant-value features for implicit regularization. Based on SeatGeek data.