Zhusuan A Library For Bayesian Deep Learning

# ZhuSuan: A Library for Bayesian Deep Learning

**arXiv ID:** 1709.05870
**Authors:** Jiaxin Shi, Jianfei Chen, Jun Zhu, Shengyang Sun, Yucen Luo, Yihong Gu, Yuhao Zhou
**Published:** 2017-09-18T11:30:08Z
**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.

## Skill Description

This skill is generated from the arXiv paper: ZhuSuan: A Library for Bayesian Deep Learning (1709.05870).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:1709.05870](http://arxiv.org/abs/1709.05870v1)