Niketkumardheeryan/ML-CaPsule

ML-capsule is a Project for beginners and experienced data science Enthusiasts who don't have a mentor or guidance and wish to learn Machine learning. Using our repo they can learn ML, DL, and many related technologies with different real-world projects and become Interview ready.

ML-CaPsule is a free, open-source learning hub for anyone wanting to practice machine learning (ML), deep learning, NLP (natural language processing), and computer vision by building real projects. It's aimed at people who don't have a mentor or want a structured, project-based way to learn.

The repo bundles three main things:

  1. 500+ real-world projects — covering topics from basics to advanced, including healthcare (Alzheimer's predictor, brain tumor detection), NLP (chatbots, fake news detection), forecasting (COVID-19, crude oil), deep learning (neural networks from scratch), and finance (Bitcoin price prediction).

  2. Curated dataset lists — organized by task type (classification, regression, NLP, computer vision, clustering, time series, recommendation systems), each with a difficulty rating and a link to download it. Beginner-friendly datasets like Iris, Titanic, and MNIST are highlighted as good starting points.

  3. Learning prerequisites and resources — step-by-step guidance for learning Python or R, with links to free courses and tutorials. The README also mentions a learning roadmap, contribution guidelines, and a code of conduct.

Tech stack: The projects use common ML/data tools: Python, TensorFlow, PyTorch, Scikit-learn, Pandas, NumPy, Jupyter, OpenCV, R, Power BI, and SQL.

Who is it for? Aspiring and experienced data science enthusiasts. The project explicitly says: "No mentor? No problem. Learn by building, become interview-ready."

Community aspects: It's MIT-licensed, welcomes pull requests (PRs), and provides contribution guidelines and project templates. There's also a "Notebook Health Check" bot mentioned in the table of contents, though the README doesn't detail how it works.

The GitHub page includes badges showing the repo is actively maintained, has many stars, forks, and open issues, and links to a project index page (docs/index.html).

Related

  • Project
    linwhitehat/ET-BERT

    A Transformer-based model for encrypted network traffic classification that learns datagram contextual relationships through pre-training and fine-tuning.

  • Project
    WillianFuks/tfcausalimpact

    A Python implementation of Google's Causal Impact algorithm using TensorFlow Probability to estimate the causal effect of interventions on time series data.

  • Project
    facebookresearch/silk

    SiLK is a self-supervised framework for learning image keypoints that emphasizes simplicity and flexibility while achieving state-of-the-art results on benchmarks. It eliminates the need for manual annotations and provides pre-trained models and tools for training, evaluation, and deployment.

  • Project
    jdtoscano94/NABLA-SciML

    A unified framework for Scientific Machine Learning (SciML) providing implementations of PINNs, DeepONets, and KANs for studying complex physical systems.