henryndubuaku/maths-cs-ai-compendium

This repository is a free, open textbook covering mathematics, computer science, and artificial intelligence from the ground up. The author created it from years of personal notes built while working in AI and machine learning, prioritizing intuition and real-world context over dense notation. Friends used earlier versions of these notes to prepare for research roles at organizations like DeepMind and OpenAI. The book is available to read online and is hosted on GitHub Pages. The compendium spans 20 chapters. The first chapters cover mathematical foundations: vectors, matrices, calculus, statistics, and probability. Later chapters move into machine learning, then into specialized areas including natural language processing, computer vision, audio and speech processing, multimodal learning, autonomous systems, and graph neural networks. The final chapters cover software engineering for production, GPU programming, AI inference optimization, and machine learning systems design. Two chapters on applied AI in healthcare and finance, plus one on emerging topics like quantum machine learning, are listed as coming soon. The intended reader is someone who wants to genuinely understand the material rather than memorize it for an exam. The author states you need only elementary mathematics and basic Python to start, and the book builds everything else from there. The foreword outlines a study approach in phases: reading after each session, reviewing notes, then testing recall without notes before moving on. The repository also includes an MCP server, which is a local knowledge-base connector that lets AI coding assistants like Claude Code or Cursor query the compendium's content directly while working. This requires a local clone of the repository. The project is open-source and accepts contributions. All content is readable in the GitHub repository or through the hosted online version.