thu-ml/Zhusuan-Jittor
Zhusuan with backend Jittor
This library helps machine learning researchers and practitioners build and train probabilistic models that combine the power of deep learning with Bayesian methods. It allows you to define complex models and then apply advanced inference techniques like Variational Inference, Importance Sampling, and Markov Chain Monte Carlo to understand uncertainties and make robust predictions. The output includes trained Bayesian deep learning models ready for analysis or deployment.
No commits in the last 6 months.
Use this if you are a machine learning researcher or data scientist working with deep learning models and need to incorporate uncertainty quantification or build more robust, interpretable models using Bayesian principles.
Not ideal if you are primarily interested in deterministic neural networks for standard supervised tasks without the need for probabilistic modeling or uncertainty estimation.
Stars
15
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 04, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/thu-ml/Zhusuan-Jittor"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
tensorflow/probability
Probabilistic reasoning and statistical analysis in TensorFlow
erdogant/bnlearn
Python package for Causal Discovery by learning the graphical structure of Bayesian networks....
pyro-ppl/pyro
Deep universal probabilistic programming with Python and PyTorch
probml/pyprobml
Python code for "Probabilistic Machine learning" book by Kevin Murphy
google/edward2
A simple probabilistic programming language.