I've been diving deep into $\color{blue}{\mathbf{Machine}}$ $\color{blue}{\mathbf{Learning}}$ whenever I can carve out time. I've done everything from building an $\color{blue}{\mathbf{LLM}}$ from $\color{blue}{\mathbf{scratch}}$ to a demand forecasting location scoring system I built during an $\color{blue}{\mathbf{internship}}$. I've been living in $\color{blue}{\mathbf{Pycharm}}$ & $\color{blue}{\mathbf{VS Code}}$ building out projects to build up my ML skillset day by day. I have high hopes of pursuing a PhD in ML.

I'm just now getting into contributing to $\color{blue}{\mathbf{open-source}}$ and coding in $\color{blue}{\mathbf{Rust}}$. I've emplemented some features and fixed some bugs over at $\color{blue}{\mathbf{Pytorch/ignite}}$ and you can usually find me doing some fixes over there.

Follow along in my journey of learning rust here: https://github.com/importstring/Learning-Rust

Aristotle-MiniGPT Tiny GPT‑style Transformer trained from scratch in PyTorch on a 1.5 MB corpus of public‑domain Aristotle. Character‑level next‑token prediction, multiple model sizes, full training logs, loss curves, and sample generations.

Digit Recognizer Simple PyTorch neural networks (MLP and CNN) trained on the Kaggle digit-recognizer dataset (MNIST in CSV format). The goal is practice with neural nets, not leaderboard sniping.

Terminal Battleship (TUI) Surprisingly complex terminal Battleship with a fully custom text UI, used as a sandbox to push code organization, modular design, and concise Python.

Predicting Heart Disease End‑to‑end ML pipeline from EDA (class balance, correlations, KDEs) to a logistic regression baseline, then tuned gradient boosting models and interpretability with SHAP.