ddbourgin/numpy-ml
Machine learning, in numpy
Implements 70+ classical and modern ML algorithms (neural networks with attention/LSTMs, tree ensembles, Gaussian processes, VAEs, reinforcement learning agents) built exclusively from NumPy and Python stdlib for educational transparency. Prioritizes algorithmic clarity over performance, with modular layer-based neural network architecture supporting optimizers, normalizers, and loss functions. Integrates with OpenAI Gym for RL training and targets prototyping workflows where understanding implementation details matters more than production speed.
16,299 stars and 447 monthly downloads. No commits in the last 6 months. Available on PyPI.
Stars
16,299
Forks
3,775
Language
Python
License
GPL-3.0
Category
Last pushed
Oct 29, 2023
Monthly downloads
447
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ddbourgin/numpy-ml"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
uxlfoundation/scikit-learn-intelex
Extension for Scikit-learn is a seamless way to speed up your Scikit-learn application
INRIA/scikit-learn-mooc
Machine learning in Python with scikit-learn MOOC
nubank/fklearn
fklearn: Functional Machine Learning
gavinkhung/machine-learning-visualized
ML algorithms implemented and derived from first-principles in Jupyter Notebooks and NumPy
workofart/ml-by-hand
A deep learning library built from scratch with complex neural networks examples built on top...