google/edward2
A simple probabilistic programming language.
This is a simple probabilistic programming language that helps researchers and machine learning engineers build and analyze deep learning models where uncertainty is important. You define your model's structure using random variables and probability distributions. The output is a flexible probabilistic program that can be manipulated for advanced training and inference, enabling things like Bayesian logistic regression or defining custom posterior distributions.
709 stars. Used by 1 other package. Available on PyPI.
Use this if you are a researcher or machine learning engineer looking to build deep learning models that explicitly account for and quantify uncertainty using probabilistic programming concepts.
Not ideal if you need a high-level, out-of-the-box solution for uncertainty modeling without wanting to delve into low-level probabilistic programming constructs.
Stars
709
Forks
75
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Jan 09, 2026
Commits (30d)
0
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/google/edward2"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
tensorflow/probability
Probabilistic reasoning and statistical analysis in TensorFlow
pyro-ppl/pyro
Deep universal probabilistic programming with Python and PyTorch
erdogant/bnlearn
Python package for Causal Discovery by learning the graphical structure of Bayesian networks....
probml/pyprobml
Python code for "Probabilistic Machine learning" book by Kevin Murphy
astro-informatics/harmonic
Machine learning assisted marginal likelihood (Bayesian evidence) estimation for Bayesian model selection