# michaelgutmann/ml-pen-and-paper-exercises

Pen and paper exercises in machine learning

Repository: https://github.com/michaelgutmann/ml-pen-and-paper-exercises
Canonical: https://ross.abutalabs.com/products/ml-pen-and-paper-exercises
Language: TeX
License Family: other
Topics: exercises-solutions, machine-learning, mathematics
Last push: 2024-05-21T20:05:42+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1528, "days_push": 834, "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 2691, forks 235 (observed 2026-08-28T04:07:10.970282+00:00)

## What it is
A collection of pen-and-paper exercises in machine learning with detailed solutions, covering linear algebra, optimisation, graphical models, inference, and Monte Carlo methods. The source is written in LaTeX and compiles to a PDF book also available on arXiv.

## Use cases
- practice machine learning math exercises with solutions
- study graphical models and variational inference problems
- find pen-and-paper exercises for a probabilistic modelling course
- learn linear algebra and optimisation for ML
- get worked solutions for hidden Markov model inference
- supplement self-study of machine learning theory

## When to choose
- you want theory-focused, math-heavy practice rather than coding exercises
- you need exercises with detailed worked solutions
- you are teaching or self-studying probabilistic machine learning

## When to avoid
- you want hands-on programming or implementation exercises
- you need deep learning or neural network practice problems
- you need a maintained software library rather than a document

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: documentation
- domain: machine-learning, mathematics, tutorials
- platform: cli
- tags: exercises, solutions, latex, probabilistic-modelling, graphical-models, variational-inference, linear-algebra, optimisation, education, linux

## Member repositories
- michaelgutmann/ml-pen-and-paper-exercises (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:10.970282+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 2026-08-30T02:16:33.743951+00:00, confidence not recorded.
  - readme: https://github.com/michaelgutmann/ml-pen-and-paper-exercises (fetched 2026-08-28T04:07:10.970282+00:00, sha 4631d9da229e)
- Data as of 2026-08-30T08:39:29.467469+00:00.