# ZhuSuan: A Library for Bayesian Deep Learning

arXiv: https://arxiv.org/abs/1709.05870 · HTML: https://mlsanity.com/paper/1709.05870/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2017.

## Built on by (most cited first, 8 of 8)

- [Pre-Trained Models: Past, Present and Future](https://mlsanity.com/paper/2106.07139/) (2021)
- [A review of machine learning in processing remote sensing data for mineral exploration](https://mlsanity.com/paper/2103.07678/) (2021)
- [Amortized Variational Inference: A Systematic Review](https://mlsanity.com/paper/2209.10888/) (2022)
- [Ivy: Templated Deep Learning for Inter-Framework Portability](https://mlsanity.com/paper/2102.02886/) (2021)
- [A Survey on Uncertainty Toolkits for Deep Learning](https://mlsanity.com/paper/2205.01040/) (2022)
- [Quantum Capsule Networks](https://mlsanity.com/paper/2201.01778/) (2022)
- [Push: Concurrent Probabilistic Programming for Bayesian Deep Learning](https://mlsanity.com/paper/2306.06528/) (2023)
- [Capsa: A Unified Framework for Quantifying Risk in Deep Neural Networks](https://mlsanity.com/paper/2308.00231/) (2023)

## Abstract (arXiv)

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.