ZhuSuan: A Library for Bayesian Deep Learning
This provides a tool for researchers and practitioners to integrate Bayesian methods with deep learning, but it is incremental as it builds on existing libraries and concepts.
The authors introduced ZhuSuan, a Python library built on TensorFlow for Bayesian deep learning, enabling probabilistic models like Bayesian logistic regression and variational auto-encoders.
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.