This repository is a curated compendium of free, high-quality reading resources for machine learning, targeting students, researchers, and practitioners. It provides a structured collection of books and papers covering foundational mathematics, statistics, various ML subfields, and practical applications, aiming to serve as a comprehensive self-study guide.

How It Works

The compendium categorizes over 185 freely available resources, including PDF books and HTML-based online books, into distinct ML domains. Resources are marked with emojis (:orange_book: for PDF, :earth_africa: for HTML) for easy identification. The organization spans core areas like EDA, mathematics, statistics, optimization, and specific ML topics such as deep learning, NLP, computer vision, and causal inference.

Quick Start & Requirements

No installation or execution is required; this is a curated list of external resources. All listed books and arXiv papers are freely accessible online.

Highlighted Details

• Comprehensive coverage across 18 categories, from foundational math to advanced topics like LLMs and conformal prediction.
• Includes both theoretical texts and practical guides with code examples (e.g., Python, R).
• Resources are clearly marked by format (PDF or HTML) for user convenience.
• Over 185 distinct resources are cataloged.

Maintenance & Community

This is a static compendium, with no active development or community interaction channels mentioned.

Licensing & Compatibility

All resources are noted as being freely available by their authors/publishers or are arXiv papers. Compatibility for commercial or closed-source use depends on the individual licenses of the linked resources.

Limitations & Caveats

The compendium is a static list and does not include interactive tools, code repositories, or community support. The availability and licensing of the linked external resources are subject to change by their respective providers.