Machine Learning & Data Science

A end-to-end MLOps pipeline for predicting telecom customer churn, featuring automated data preprocessing, ML model training, experiment tracking with MLflow, distributed training using PySpark, real-time inference via Kafka streaming, Airflow DAG orchestration, and Dockerized REST API deployment.

Machine Learning Systems: Foundations, Scaling, Agentic AI, and Physical AI (Vols I–IV) • Harvard CS249r | https://mlsysbook.ai

This repo is based on https://github.com/yunjey/pytorch-tutorial, but add jupyter notebooks and detailed explanation of PyTorch APIs

Student Performance Prediction System using Machine Learning

Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine

Diffusion-based synthetic RF signal generation to improve modulation classification

Training-free Spectrum acceleration for ComfyUI’s native MiniMax H3 audio-video model. Uses Chebyshev ridge feature forecasting to skip selected H3 transformer evaluations, with adaptive scheduling, sampler-aware support for Euler, ER-SDE, RES, SEEDS and SA-Solver, CPU/VRAM history storage, and fail

Stable Diffusion web UI

A complete, structured hub for learning Artificial Intelligence — covering AI, Machine Learning, Deep Learning, and Data Science with books, roadmaps, and curated resources from beginner to advanced.

Machine Learning (AI) Scraper helper service for changedetection.io

The Open Source Feature Store for AI/ML

Gorgonia is a library that helps facilitate machine learning in Go.

YuE2: frontier music generation with symbolic planning, zero-shot covers, and agentic music editing.

Postgres with GPUs for ML/AI apps.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Formulate trained predictors in Gurobi models

A visual, interactive atlas of data science concepts.

Generative AI satellite cloud removal system using SAR-guided diffusion bridges for ISRO LISS-IV imagery — ISRO Bharatiya Antariksh Hackathon 2026 Grand Finale Finalist

AI comic and manga translator app/browser extension for automatically translating comics, manga, manhwa, BDs, fumetti, and more in multiple languages and formats (Images, PDF, EPUB, CBR, CBZ etc).

Experimental causal-inference research on financial regimes: PCMCI+, ICP and causal forests over market data (work in progress)

Malware Mutation Using Reinforcement Learning and Generative Adversarial Networks

Analysis and prediction of student final scores using Linear Regression | Python, Pandas, Scikit-learn | R² Score: ~0.79

Forecasted product sales using time series models such as Holt-Winters, SARIMA and causal methods, e.g. Regression. Evaluated performance of models using forecasting metrics such as, MAE, RMSE, MAPE and concluded that Linear Regression model produced the best MAPE in comparison to other models

scikit-learn-compatible time-series cross-validation: purging, embargo, combinatorial purged CV, and deflated Sharpe ratios

This repository is a curated collection of hands-on data science projects tailored for beginners. Whether you're just starting your journey in data science or looking to strengthen your skills, these projects provide a practical and interactive way to apply your knowledge.

An intelligent pricing recommendation engine designed for independent consultants, technical mentors, and digital freelancers in emerging markets like Kenya.

A powerful software to analise and predict good investiments using Machine Learning.

Infrastructure for continually self‑improving agents

A Python open-source project for “the road to learning programming on your own,” with a comprehensive tutorial: AI lab, valuable videos, data structures, learning guides, hands-on machine learning, hands-on deep learning, web scraping, big-tech interview experiences, programmer life, and resource sharing.

Differentiable signal processing on the sphere for PyTorch

This repository was built with Claude for the Data Science and Artificial Intelligence course at Anvisa as part of PROADI-SUS.

The PyTorch-based audio source separation toolkit for researchers

[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

A machine learning project that predicts car prices based on various features using Python and Scikit-learn.

Computer Vision Annotation Tool (CVAT) is a leading platform for building high-quality visual datasets for vision AI. It offers open-source, cloud, and enterprise products, as well as labeling services, for image, video, and 3D annotation with AI-assisted labeling, quality assurance, team collaborat

End-to-end quantitative sports betting pipeline for the Premier League. Probabilistic modeling (Poisson, XGBoost, Dense NN), Dixon-Coles adjustment, and Fractional Kelly portfolio optimization with turnover tax constraints.

10 Weeks, 20 Lessons, Data Science for All!

Create adversarial attacks against machine learning Windows malware detectors

Digital Audio Workstation with Python; VST instruments/effects, parameter automation, FAUST, JAX, Warp Markers, and JUCE processors

A comprehensive collection of Machine Learning materials, tutorials, and practical implementations designed for learning and mastering ML fundamentals and advanced techniques.

Official code for "Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection" (NeurIPS 2026). RAMSAD selects the best anomaly detector for a new series by retrieving similar series from a knowledge base, with no selector training.

Bank loan portfolio analysis: Python (pandas) cleaning, PostgreSQL KPI queries, and a two-page interactive Excel dashboard (summary + overview).

[CVPR 2026] Official release of "Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning"

Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning,

Type-safe, distributed orchestration of agents, ML pipelines, and real-time inference on your k8s — in pure Python with async/await, also other languages (rust, go and ts)

Open3D: A Modern Library for 3D Data Processing

This project explores the potential for identifying stock market regimes , predicting stock market regimes and backtesting trading strategies based on those predictions.

SeisBench - A toolbox for machine learning in seismology

Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking