M

machine-learning

A production-grade machine learning system for classifying celestial objects — stars, galaxies, and quasars — from 500,000 photometric observations sourced from the Sloan Digital Sky Survey (SDSS DR18). The pipeline covers LOF-based outlier detection, SMOTEENN class balancing, and SelectKBest feature selection, with six classifier configurations benchmarked against each other. Random Forest achieved the highest accuracy at ~99.51%, while LightGBM was selected for deployment due to its faster inference, smaller footprint, and clean ONNX export path. The system is fully containerized with Docker, backed by a CI/CD pipeline, and served live via a Gradio interface on Hugging Face Spaces.

Self-hosted forecasting + prediction service. Five zero-shot time-series foundation models (Chronos-2, TimesFM 2.5, Moirai-2, Toto-1, Sundial) across six forecast types, plus nine supervised tabular ML backends (LightGBM, XGBoost, sklearn family) with calibrated / stacking / diversified meta-learners. Unified REST API + MCP server.

Introduction to classification using machine learning and deep learning (PyTorch, TensorFlow, Keras)

Try get list Tools from MCP server

A CLI tool to query and install different language voices for piper speech synthesizer (https://github.com/rhasspy/piper)

Machine Learning toolbox for Humans

https://github.com/yandex/rep

Provide a good solution to the CFM 2020 Challenge the hard way (hand writing the optimizer, directly use the Linear Algebra routines, use the most out of the multicore hardware).

A pyGTK and vlc based application to hand-annotate audio and video files for classification tasks. https://pypi.org/project/pyMediaAnnotator/

Simple and efficient data recording for OpenAI Gym reinforcement learning environments. https://doctorj.gitlab.io/gymbag/