# datawhalechina/key-book

《机器学习理论导引》（宝箱书）的证明、案例、概念补充与参考文献讲解。

Repository: https://github.com/datawhalechina/key-book
Canonical: https://ross.abutalabs.com/products/key-book
Homepage: https://datawhalechina.github.io/key-book/
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Topics: machine-learning, deep-learning, artificial-intelligence, theoretical-machine-learning, course, tutorial
Last push: 2026-08-19T23:31:03+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 8, longevity 100
- inputs: {"age_days": 2273, "days_push": 14, "days_rel": 525, "gap_med": null, "n_releases_24m": 1}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1718, forks 190 (observed 2026-08-28T04:05:26.545879+00:00)

## What it is
Key-book is a companion study guide (in Chinese) for the textbook 'An Introduction to Theoretical Machine Learning', providing concept explanations, supplementary proofs, and worked examples. It is published as Jupyter Notebooks and an online book/PDF by the Datawhale open-source education community.

## Use cases
- understand PAC learnability theory with supplementary notes
- get detailed proofs for machine learning theory textbook chapters
- learn VC dimension and Rademacher complexity concepts
- study generalization bounds and algorithm stability
- build theoretical foundations after practical ML experience
- find worked examples for online learning regret bounds

## When to choose
- you are reading 'An Introduction to Theoretical Machine Learning' and need help with proofs
- you want a free, structured introduction to machine learning theory
- you prefer explanations with examples alongside abstract theorems

## When to avoid
- you need practical ML engineering tutorials or code frameworks
- you want an English-language resource
- you need a comprehensive standalone ML theory textbook rather than companion notes

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation
- domain: machine-learning, tutorials, mathematics, artificial-intelligence
- platform: python
- tags: companion-notes, machine-learning-theory, jupyter-notebook, chinese, datawhale, textbook-notes, proofs, pac-learning, education, web-server

## Member repositories
- datawhalechina/key-book (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:26.545879+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:34:09.969668+00:00, confidence not recorded.
  - readme: https://github.com/datawhalechina/key-book (fetched 2026-08-28T04:05:26.545879+00:00, sha 342df64962b1)
  - homepage: https://datawhalechina.github.io/key-book/ (fetched 2026-08-29T11:10:05.411902+00:00, sha 9c8d859d9c15)
- Data as of 2026-08-30T08:39:29.467469+00:00.