What it does

This repo is a personal study journal turned public reference: roughly two dozen Markdown files explaining machine learning and deep learning algorithms in Chinese. The author groups them into regression, decision trees, Bayesian methods, clustering, neural networks (BP, RBF, SOM, ART, Hopfield), and more. Think lecture notes, not library.

The interesting bit

The breadth is almost comically encyclopedic for a solo project—PageRank sits next to AdaBoost, rough sets next to EM. The author explicitly frames it as a book-in-progress for developers intimidated by AI’s salary hype and actual difficulty. There’s something honest about admitting the field is hard and just… taking notes in public.

Key highlights

• Covers 30+ algorithms from KNN to AlphaGo Zero references
• Organized by algorithm family (regression, trees, kernels, clustering, etc.)
• Written in Chinese; assumes probability/stats background
• Includes environment setup guides for ML and deep learning
• Explicitly ongoing: “subsequent chapters will be continuously supplemented”

Caveats

• No runnable code, no datasets, no implementations—pure exposition
• Several linked sections (“应用案例”, etc.) appear empty or are placeholders
• Last substantial update timing is unclear from the README

Verdict

Worth a skim if you read Chinese and want a structured checklist of classical ML topics to research elsewhere. Skip it if you need working code, modern deep learning frameworks, or anything past 2017-era algorithm coverage.