# aespresso/a_journey_into_math_of_ml

汉语自然语言处理视频教程-开源学习资料

Repository: https://github.com/aespresso/a_journey_into_math_of_ml
Canonical: https://ross.abutalabs.com/products/a_journey_into_math_of_ml
Homepage: https://space.bilibili.com/255296093
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2019-09-29T02:24:52+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2659, "days_push": 2531, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1717, forks 693 (observed 2026-08-28T04:05:26.423484+00:00)

## What it is
A collection of Chinese-language machine learning tutorials in Jupyter Notebook form, accompanied by video lectures on YouTube and Bilibili. It covers mathematical foundations like maximum likelihood, logistic regression, and AdaBoost, plus Chinese NLP topics including Transformers, BERT, and HMM-based named entity recognition.

## Use cases
- learn the math behind machine learning from scratch
- understand the transformer architecture with visual explanations
- study BERT and language model pretraining in Chinese
- learn hidden Markov models for named entity recognition
- understand the Viterbi algorithm for sequence labeling
- visualize maximum likelihood estimation in 3D
- learn logistic regression with cross-entropy and gradient descent

## When to choose
- you prefer Chinese-language explanations of ML and NLP concepts
- you want math-first derivations paired with runnable notebooks and videos
- you are studying classical NLP models like HMM and transformer from the ground up

## When to avoid
- you need production-ready ML code or maintained libraries
- you require English-language tutorials
- you need up-to-date coverage of modern LLM techniques

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, nlp, data-visualization
- domain: machine-learning, tutorials, education
- platform: python
- tags: jupyter-notebooks, chinese-language, video-tutorials, transformer, bert, hmm, logistic-regression, adaboost, maximum-likelihood, natural-language-processing

## Member repositories
- aespresso/a_journey_into_math_of_ml (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:26.423484+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 2026-08-30T03:34:12.228899+00:00, confidence not recorded.
  - readme: https://github.com/aespresso/a_journey_into_math_of_ml (fetched 2026-08-28T04:05:26.423484+00:00, sha 1e2a91663d6e)
- Data as of 2026-08-30T08:39:29.467469+00:00.