thu-ml/zhusuan

A probabilistic programming library for Bayesian deep learning, generative models, based on Tensorflow

50
/ 100
Established

This library helps machine learning researchers and practitioners build and experiment with advanced probabilistic models, especially those involving deep neural networks. It takes a description of your model's structure and data, and provides tools to estimate its parameters and make predictions. This is ideal for researchers developing new deep generative models or Bayesian deep learning architectures.

2,220 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or data scientist needing to implement and experiment with probabilistic deep learning models and advanced Bayesian inference algorithms like Variational Inference, Importance Sampling, or Hamiltonian Monte Carlo.

Not ideal if you primarily work with standard deterministic neural networks for supervised tasks or need a more out-of-the-box solution for common machine learning problems without deep customization of probabilistic aspects.

probabilistic-modeling bayesian-deep-learning generative-models machine-learning-research statistical-inference
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

2,220

Forks

416

Language

Python

License

MIT

Last pushed

Dec 17, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/thu-ml/zhusuan"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.