Towards Bayesian Deep Learning: A Framework and Some Existing Methods

Wang Hao, Dit Yan Yeung

Research output: Contribution to journalArticlepeer-review

68 Scopus citations


While perception tasks such as visual object recognition and text understanding play an important role in human intelligence, subsequent tasks that involve inference, reasoning, and planning require an even higher level of intelligence. The past few years have seen major advances in many perception tasks using deep learning models. For higher-level inference, however, probabilistic graphical models with their Bayesian nature are still more powerful and flexible. To achieve integrated intelligence that involves both perception and inference, it is naturally desirable to tightly integrate deep learning and Bayesian models within a principled probabilistic framework, which we call Bayesian deep learning. In this unified framework, the perception of text or images using deep learning can boost the performance of higher-level inference and in return, the feedback from the inference process is able to enhance the perception of text or images. This paper proposes a general framework for Bayesian deep learning and reviews its recent applications on recommender systems, topic models, and control. In this paper, we also discuss the relationship and differences between Bayesian deep learning and other related topics such as the Bayesian treatment of neural networks.

Original languageEnglish (US)
Pages (from-to)3395-3408
Number of pages14
JournalIEEE Transactions on Knowledge and Data Engineering
Issue number12
StatePublished - Dec 1 2016
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Computer Science Applications
  • Computational Theory and Mathematics


  • Artificial intelligence
  • Bayesian networks
  • data mining
  • deep learning
  • machine learning
  • neural networks


Dive into the research topics of 'Towards Bayesian Deep Learning: A Framework and Some Existing Methods'. Together they form a unique fingerprint.

Cite this