A Survey on Bayesian Deep Learning

By Hao Wang, Dit-Yan Yeung. ACM Computing Surveys, 2016

316 citations recorded by the source corpus.

A comprehensive artificial intelligence system needs to not only perceive the environment with different “senses” (e.g., seeing and hearing) but also infer the world’s conditional (or even causal) relations and corresponding uncertainty. The past decade has seen major advances in many perception tasks, such as visual object recognition and speech recognition, using deep learning models. For higher-level inference, however, probabilistic graphical models with their Bayesian nature are still more powerful and flexible. In recent years, Bayesian deep learning has emerged as a unified probabilistic framework to tightly integrate deep learning and Bayesian models.1 In this general framework, the perception of text or images using deep learning can boost the performance of higher-level inference and, in turn, the feedback from the inference process is able to enhance the perception of text or images. This survey provides a comprehensive introduction to Bayesian deep learning and reviews its recent applications on recommender systems, topic models, control, and so on. We also discuss the relationship and differences between Bayesian deep learning and other related topics, such as Bayesian treatment of neural networks.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/b0e6fd0c22865fa8ca7a02d18681087052c9f6c5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluation (2023, background): “In the last decade, there have been major advances in Bayesian deep learning [351, 352, 353, 341].”
Hands-On Bayesian Neural Networks—A Tutorial for Deep Learning Users (2020, background): “There is a rich literature about BNNs and the related ﬁeld of Bayesian deep learning, which is referred to by Wang and Yeung [11] as the conjoint use of deep learning for perception and traditional Bayesian models for inference.”
Remote patient monitoring using artificial intelligence: Current state, applications, and challenges (2023, methodology): “The review article discussed ensemble techniques and Bayesian techniques like Bayesian deep learning (BDL) (H. Wang & Yeung, 2016) and Bayesian NNs (BNNs) (K. C. Wang et al., 2018) to address the reliability issue of the deep learning models and can interpret their hyperparameters.”
A survey of uncertainty in deep neural networks (2021, background): “contributed two surveys on Bayesian deep learning [53], [54].”
A review of machine learning in processing remote sensing data for mineral exploration (2021, background): “Recently, there has been tremendous progress in the area of Bayesian neural networks and Bayesian deep learning (Wang and Yeung, 2020; Shi et al., 2017); however, these methods have not been much”
Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection (2021, background): “That is, we first obtain initial estimates and quantify the corresponding uncertainties with the probabilistic representational model [23, 24, 51].”
Visual Attention Methods in Deep Learning: An In-Depth Survey (2022, methodology): “Stochastic methods show better performance when optimized well [108, 170].”