项目简介
一本非传统、直觉优先的教科书，涵盖从基础到高级的数学、计算和人工智能。面向追求深度理解的实践者，包括向量、矩阵、微积分、机器学习、自然语言处理、计算机视觉等章节。
README 预览
# Maths, CS & AI Compendium\n\n\n\n**Read online**: [henryndubuaku.github.io/maths-cs-ai-compendium](https://henryndubuaku.github.io/maths-cs-ai-compendium/)\n\n## Overview\nMost textbooks bury good ideas under dense notation, skip the intuition, assume you already know half the material, and quickly get outdated in fast-moving fields like AI. This is an open, unconventional textbook covering maths, computing, and artificial intelligence from the ground up. Written for curious practitioners looking to deeply understand the stuff, not just survive an exam/interview. \n\n## Background\nOver the past years working in AI/ML, I filled notebooks with intuition first, real-world context, no hand-waving explanations of maths, computing and AI concepts. In 2025, a few friends used these notes to prep for interviews at DeepMind, OpenAI, Nvidia etc. They all got in and currently perform well in their roles. Meanwhile I got in Y Combinator last year. So I'm sharing to everyone.\n\n## MCP Server\nThis repo includes an MCP server that lets any AI assistant (Claude Code, Cursor, VS Code, etc.) use the compendium as a knowledge base. It requires a local clone of the repo. Comes with tools for educational purposes and example implementations.\n\n## Outline \n\n| # | Chapter | Summary | Status |\n|---|---------|---------|--------|\n| 01 | [Vectors](chapter%2001%3A%20vectors/01.%20vector%20spaces.md) | Spaces, magnitude, direction, norms, metrics, dot/cross/outer products, basis, duality | Available |\n| 02 | [Matrices](chapter%2002%3A%20matrices/01.%20matrix%20properties.md) | Properties, special types, operations, linear transformations, decompositions (LU, QR, SVD) | Available |\n| 03 | [Calculus](chapter%2003%3A%20calculus/01.%20differential%20calculus.md) | Derivatives, integrals, multivariate calculus, Taylor approximation, optimisation and gradient descent | Available |\n| 04 | [Statistics](chapter%2004%3A%20statistics/01.%20fundamentals.md) | Descriptive measures, sampling, ce
常见问题 (1)
故障排除如何修复 Windows 上因文件或文件夹名称中包含冒号而导致的 Git clone 失败？
故障排除
如何修复 Windows 上因文件或文件夹名称中包含冒号而导致的 Git clone 失败？Windows 不允许在文件或目录名称中使用冒号（:），因此包含诸如 chapter NN: description 这类路径的仓库会无法克隆或检出。请在支持冒号的系统上重命名受影响的路径，使用 Windows 安全的分隔符，例如将 chapter 01: Introduction 改为 chapter 01 - Introduction。使用 git add -A 和 git commit 提交此次重命名，然后更新所有指向旧路径的 README 或文档链接。之后 Windows 用户即可克隆或拉取修复后的仓库。