trekhleb/homemade-machine-learning resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

24781 stars · 4193 forks observed · 2026-08-28

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

A collection of popular machine learning algorithms implemented from scratch in Python, with the underlying mathematics explained. Each algorithm comes with interactive Jupyter Notebook demos for experimenting with training data and visualizing results in the browser.

Use cases

• learn how machine learning algorithms work under the hood
• understand the math behind linear regression and logistic regression
• implement k-means and neural networks from scratch
• find interactive jupyter demos of ml algorithms
• study machine learning fundamentals with code examples
• practice implementing ml algorithms without libraries

When to choose

• you want to deeply understand the mathematics behind ML algorithms
• you prefer learning through readable, from-scratch implementations
• you want interactive notebooks to experiment with parameters and see charts
• you are studying Andrew Ng's machine learning course and want code practice

When to avoid

• you need production-ready, optimized ML implementations
• you want a library with one-liner APIs like scikit-learn
• you need GPU-accelerated or distributed training
• you require guaranteed maintenance and up-to-date dependencies

Facets

learning-resource · maturity maintenance

machine-learning data-visualization math machine-learning education tutorials python from-scratch-implementations jupyter-notebooks interactive-demos supervised-learning unsupervised-learning neural-networks educational algorithms jupyter

Member repositories

For agents

markdown · JSON · MCP: product_card(name="trekhleb/homemade-machine-learning")