eriklindernoren/ML-From-Scratch

★33,330Python🇪🇺 EuropeMIT⑂ 5,546Issue 45Updated Oct 15, 2023

View on GitHub ↗

Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.

A readable NumPy library covering regression to deep learning basics — This repo reimplements classic ML and deep learning algorithms—regression, CNNs, GANs, reinforcement learning, genetic algorithms—using bare NumPy, prioritizing transparency over speed. It's aimed at learners who want to see the actual math and logic behind models rather than use optimized black-box libraries.

Metrics

Retention can be computed 30 days after a repository first trends (it isn't shown until then). See About for how each metric is defined.

Star growth and Trending appearances (last 30 days)

Created Feb 5, 2017 · First on trending Nov 2, 2026

Other notable repositories in the same category (Learning & resources)

• amananandrai/system-design-explainerExplore 30+ Real-World Architectures With Swappable Cloud Stacks
• AbdullahAlhariri/penmentorA Pen-Tablet Math Tutor That Marks and Animates Your Work
• panda-sai/vb-dsa-visualWatch Data Structures Animate Step by Step in the Browser
• chandansgowda/learn-git-in-kannadaGit and GitHub basics explained from scratch in Kannada
• epoyraz/nes-contra-usA Byte-for-Byte Annotated Disassembly of NES Contra (US)

See all Learning & resources repositories →

Rank within data-science

See all data-science repositories →