# gavinkhung/machine-learning-visualized

ML algorithms implemented and derived from first-principles in Jupyter Notebooks and NumPy

Repository: https://github.com/gavinkhung/machine-learning-visualized
Canonical: https://ross.abutalabs.com/products/machine-learning-visualized
Homepage: https://ml-visualized.com/
Language: TeX
License: MIT
License Family: permissive
Topics: book, jupyter-notebook, latex, machine-learning, numpy, python, neural-network
Last push: 2026-08-19T03:16:18+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 35, longevity 38
- inputs: {"age_days": 536, "days_push": 14, "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 1929, forks 179 (observed 2026-08-28T04:05:55.996562+00:00)

## What it is
A Jupyter Book website that implements and mathematically derives machine learning algorithms from first principles using Jupyter Notebooks and NumPy, with visualizations of training convergence. It aggregates notebooks from separate per-algorithm repositories and includes interactive Marimo notebooks for exploring weights and loss functions.

## Use cases
- learn how neural networks work from first principles
- visualize gradient descent converging on optimal weights
- understand backpropagation math step by step
- study logistic regression and perceptron derivations
- see interactive loss landscape visualizations
- build an EPUB or website of ML algorithm notebooks
- learn PCA and k-means clustering with visual walkthroughs

## When to choose
- you want to learn ML algorithms mathematically rather than via high-level libraries
- you prefer visual, notebook-based explanations of training dynamics
- you want NumPy-only implementations without framework abstractions
- you need a free open-source ML textbook with interactive elements

## When to avoid
- you need production-ready ML code or a reusable library
- you want GPU-accelerated or deep learning framework tooling like PyTorch
- you need comprehensive coverage of modern topics like transformers or LLMs

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, data-visualization, developer-tools
- domain: machine-learning, deep-learning, tutorials, education, data-visualization
- platform: python, cross-platform
- tags: jupyter-book, jupyter-notebooks, numpy, first-principles, neural-networks, interactive-notebooks, marimo, epub, web-server

## Member repositories
- gavinkhung/machine-learning-visualized (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:55.996562+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 2026-08-30T03:09:02.310879+00:00, confidence not recorded.
  - readme: https://github.com/gavinkhung/machine-learning-visualized (fetched 2026-08-28T04:05:55.996562+00:00, sha 9f274a008d8b)
  - homepage: https://ml-visualized.com/ (fetched 2026-08-29T10:48:23.181200+00:00, sha 86a31a4eff3a)
- Data as of 2026-08-30T08:39:29.467469+00:00.