本文是知乎上浙大Ziyue Wu对A Survey on Bayesian Deep Learning这篇综述论文的解读。从Arxiv提交记录来看,后者最早版本是2016年的,到今年9月正式在ACM Computing Surveys上发表。
一个综合的人工智能系统应该不止能“感知”环境,还要能“推断”关系及其不确定性。深度学习在各类感知的任务中表现很不错,如图像识别,语音识别。然而概率图模型更适用于inference的工作。这篇survey提供了贝叶斯深度学习(Bayesian Deep Learning, BDL)的基本介绍以及其在推荐系统,话题模型,控制等领域的应用。 本文的目录如下:
- 1 Introduction
- 2 Deep Learning
- 3 Probabilistic Graphical Models
- 4 Bayesian Deep Learning
- 4.1 A Brief History of Bayesian Neural Networks and Bayesian Deep Learning
- 4.2 General Framework
- 4.3 Perception Component
- 4.4 Task-Specific Component
- 5 Concrete BDL Models and Applications
- 5.1 Supervised Bayesian Deep Learning for Recommender Systems
- 5.2 Unsupervised Bayesian Deep Learning for Topic Models
- 5.3 Bayesian Deep Representation Learning for Control
- 5.4 Bayesian Deep Learning for Other Applications
- 6 Conclusions and Future Research
感兴趣的可以戳链接继续阅读。
内容中包含的图片若涉及版权问题,请及时与我们联系删除
评论
沙发等你来抢