rushter/MLAlgorithms resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

11171 stars · 1768 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

learning-resource · maturity maintenance

machine-learning deep-learning reinforcement-learning data-science machine-learning deep-learning education python cross-platform from-scratch-implementations numpy scipy educational algorithms neural-networks svm gradient-boosting kmeans pca

Member repositories

For agents

markdown · JSON · MCP: product_card(name="rushter/MLAlgorithms")