# rushter/MLAlgorithms

Minimal and clean examples of machine learning algorithms implementations

Repository: https://github.com/rushter/MLAlgorithms
Canonical: https://ross.abutalabs.com/products/mlalgorithms
Language: Python
License: MIT
License Family: permissive
Topics: machine-learning, deep-learning, neural-networks, machine-learning-algorithms, python
Last push: 2026-05-07T06:48:35+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 81, release rhythm 35, longevity 100
- inputs: {"age_days": 3619, "days_push": 118, "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 11171, forks 1768 (observed 2026-08-28T04:10:46.277454+00:00)

## What it is
A collection of minimal, clean Python implementations of core machine learning algorithms built with numpy, scipy, and autograd. It is designed for people who want to learn algorithm internals or implement ML algorithms from scratch rather than use optimized production libraries.

## Use cases
- learn how machine learning algorithms work internally
- implement ML algorithms from scratch
- study readable neural network code including CNN and LSTM
- understand how gradient boosting or random forests work under the hood
- explore reinforcement learning with deep Q-learning examples
- teach a machine learning course with simple reference code

## When to choose
- you want readable, educational implementations instead of optimized library code
- you are learning ML internals or preparing for interviews
- you need simple reference code to base your own implementations on

## When to avoid
- you need production-grade performance or GPU acceleration
- you want a maintained library with full API stability for real applications
- you need comprehensive model evaluation, preprocessing, or deployment tooling

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, reinforcement-learning, data-science
- domain: machine-learning, deep-learning, education
- platform: python, cross-platform
- tags: from-scratch-implementations, numpy, scipy, educational, algorithms, neural-networks, svm, gradient-boosting, kmeans, pca

## Member repositories
- rushter/MLAlgorithms (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:46.277454+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 2026-08-29T17:16:44.050904+00:00, confidence not recorded.
  - readme: https://github.com/rushter/MLAlgorithms (fetched 2026-08-28T04:10:46.277454+00:00, sha 21d591da63ca)
- Data as of 2026-08-30T08:39:29.467469+00:00.