ddbourgin/numpy-ml
A collection of machine learning algorithms implemented from scratch using only NumPy.
Not currently ranked — collecting fresh signals.
star history
numpy-ml is an educational and prototyping library that reimplements common machine learning algorithms without external ML dependencies. It covers neural network layers (LSTM, CNN, ResNet, attention, VAE, WGAN-GP), Bayesian methods (Gaussian processes, mixture models), sequence models (HMMs, topic modeling via LDA), and reinforcement learning agents that train in OpenAI Gym environments. All implementations prioritize legibility over performance, serving as a starting point for ML experimentation.
Frequently asked
- What is ddbourgin/numpy-ml?
- A collection of machine learning algorithms implemented from scratch using only NumPy.
- Is numpy-ml open source?
- Yes — ddbourgin/numpy-ml is open source, released under the GPL-3.0 license.
- What language is numpy-ml written in?
- ddbourgin/numpy-ml is primarily written in Python.
- How popular is numpy-ml?
- ddbourgin/numpy-ml has 16.3k stars on GitHub.
- Where can I find numpy-ml?
- ddbourgin/numpy-ml is on GitHub at https://github.com/ddbourgin/numpy-ml.