eriklindernoren/ML-From-Scratch
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.
Implements supervised, unsupervised, reinforcement learning, and deep learning algorithms including CNNs, GANs, RBMs, and deep Q-networks entirely with NumPy and basic Python—no framework dependencies. Each model includes modular layer abstractions (Conv2D, Dense, BatchNormalization, Dropout) that can be composed into larger architectures, with built-in training loops and visualization examples. Designed for educational purposes with transparent algorithm implementations that prioritize clarity over performance optimization.
31,023 stars. No commits in the last 6 months.
Stars
31,023
Forks
5,205
Language
Python
License
MIT
Category
Last pushed
Oct 15, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/eriklindernoren/ML-From-Scratch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
uxlfoundation/scikit-learn-intelex
Extension for Scikit-learn is a seamless way to speed up your Scikit-learn application
ddbourgin/numpy-ml
Machine learning, in numpy
INRIA/scikit-learn-mooc
Machine learning in Python with scikit-learn MOOC
nubank/fklearn
fklearn: Functional Machine Learning
workofart/ml-by-hand
A deep learning library built from scratch with complex neural networks examples built on top...