Transformer from scratch
A character-level GPT-style transformer implemented in PyTorch, including attention, positional encoding, training, evaluation, and generation.
Source ↗Selected work
Projects are listed with their current state and source code. GitHub contains the full history, experiments, and smaller repositories.
A numbered series of focused machine learning projects. Projects are added here as the work is completed.
A character-level GPT-style transformer implemented in PyTorch, including attention, positional encoding, training, evaluation, and generation.
Source ↗AG News analysis with pre-model hypotheses, TF-IDF and logistic regression, error analysis, ROC/AUC, and LIME. Test accuracy: 91.78%.
Source ↗The Project 2 model served through FastAPI with Pydantic validation, tests, Docker, model documentation, and a Railway deployment.
Source ↗The next entry will be added when there is working code and something useful to report.
Research, local tools, learning environments, and hardware experiments.
Five transparent event-data dimensions for comparing Premier League teams, with tactical neighbours and grounded AI explanations.
Source ↗Cross-dataset comparison of mBERT and MuRIL for code-mixed language.
Source ↗A local-first macOS desktop agent with local model discovery and safety confirmations.
Source ↗An interactive WebGL environment for learning twisty-puzzle notation and algorithms.
Source ↗An interactive mechanics lab with an analytical solver and conservation tests.
Source ↗A retrieval tool that explains football decisions using the IFAB Laws of the Game.
Source ↗A raw coordinate and pressure diagnostic for an ESP32 resistive touchscreen.
Source ↗A recent TypeScript project exploring practical engineering evaluation.
Source ↗