# roboticcam/machine-learning-notes

My continuously updated Machine Learning, Probabilistic Models and Deep Learning notes and demos (2000+ slides)  我不间断更新的机器学习，概率模型和深度学习的讲义(2000+页)和视频链接

Repository: https://github.com/roboticcam/machine-learning-notes
Canonical: https://ross.abutalabs.com/products/machine-learning-notes
Language: Jupyter Notebook
License Family: other
Last push: 2026-07-08T15:37:42+00:00

## Health v2 (maintenance only)
Score: 73/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 91, release rhythm 35, longevity 100
- inputs: {"age_days": 3121, "days_push": 56, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 10344, forks 1826 (observed 2026-08-28T04:10:41.710834+00:00)

## What it is
A continuously updated collection of 2000+ slides, Jupyter Notebook demos, and video links covering machine learning, probabilistic models, deep learning, generative AI, and learning theory. The material is bilingual (English and Mandarin) and accompanies live-streamed research seminars.

## Use cases
- learn machine learning theory from lecture slides
- study transformers and attention mechanisms with PyTorch code
- understand variational inference, VAEs, and diffusion models
- prepare for ML PhD-level research training
- find bilingual (Chinese/English) deep learning course material
- review concentration inequalities, PAC Bayes, and neural tangent kernels

## When to choose
- you want mathematically rigorous, theory-heavy ML notes with code demos
- you prefer learning from slides plus recorded video lectures
- you need coverage of both classical probabilistic models and modern generative AI

## When to avoid
- you need a software library or tool rather than educational material
- you want beginner-friendly tutorials without linear algebra, calculus, and probability prerequisites
- you need licensed or formally peer-reviewed course content

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, deep-learning, data-science, nlp
- domain: machine-learning, deep-learning, artificial-intelligence, tutorials, education
- platform: python
- tags: lecture-notes, slides, jupyter-notebooks, probabilistic-models, generative-models, transformers, variational-inference, learning-theory, bilingual

## Member repositories
- roboticcam/machine-learning-notes (main) score 73

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:41.710834+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 2026-08-29T17:19:08.518487+00:00, confidence not recorded.
  - readme: https://github.com/roboticcam/machine-learning-notes (fetched 2026-08-28T04:10:41.710834+00:00, sha 04fe59a71091)
- Data as of 2026-08-30T08:39:29.467469+00:00.