ZhuSuan: A Library for Bayesian Deep Learning
Abstract
In this paper we introduce ZhuSuan, a python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and deep learning. ZhuSuan is built upon Tensorflow. Unlike existing deep learning libraries, which are mainly designed for deterministic neural networks and supervised tasks, ZhuSuan is featured for its deep root into Bayesian inference, thus supporting various kinds of probabilistic models, including both the traditional hierarchical Bayesian models and recent deep generative models. We use running examples to illustrate the probabilistic programming on ZhuSuan, including Bayesian logistic regression, variational auto-encoders, deep sigmoid belief networks and Bayesian recurrent neural networks.
- Publication:
-
arXiv e-prints
- Pub Date:
- September 2017
- DOI:
- 10.48550/arXiv.1709.05870
- arXiv:
- arXiv:1709.05870
- Bibcode:
- 2017arXiv170905870S
- Keywords:
-
- Statistics - Machine Learning;
- Computer Science - Artificial Intelligence;
- Computer Science - Machine Learning;
- Computer Science - Neural and Evolutionary Computing;
- Statistics - Computation
- E-Print:
- The GitHub page is at https://github.com/thu-ml/zhusuan