University of Oulu

Moloud Abdar, Farhad Pourpanah, Sadiq Hussain, Dana Rezazadegan, Li Liu, Mohammad Ghavamzadeh, Paul Fieguth, Xiaochun Cao, Abbas Khosravi, U. Rajendra Acharya, Vladimir Makarenkov, Saeid Nahavandi, A review of uncertainty quantification in deep learning: Techniques, applications and challenges, Information Fusion, Volume 76, 2021, Pages 243-297, ISSN 1566-2535,

A review of uncertainty quantification in deep learning : techniques, applications and challenges

Saved in:
Author: Abdar, Moloud1; Pourpanah, Farhad2; Hussain, Sadiq3;
Organizations: 1Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Geelong, Australia
2College of Mathematics and Statistics, Guangdong Key Lab. of Intelligent Information Processing, Shenzhen University, China
3System Administrator, Dibrugarh University, Dibrugarh, India
4Department of Computer Science and Software Engineering, Swinburne University of Technology, Melbourne, Australia
5Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland
6Google Research, Google, USA
7Department of Systems Design Engineering, University of Waterloo, Waterloo, Canada
8State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
9Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, Clementi, Singapore
10Department of Biomedical Engineering, School of Science and Technology, SUSS University, Singapore
11Department of Biomedical Informatics and Medical Engineering, Asia University, Taichung, Taiwan
12Department of Computer Science, University of Quebec in Montreal, Montreal (QC), Canada
Format: article
Version: published version
Access: open
Online Access: PDF Full Text (PDF, 2.9 MB)
Persistent link:
Language: English
Published: Elsevier, 2021
Publish Date: 2021-09-06


Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of uncertainties during both optimization and decision making processes. They have been applied to solve a variety of real-world problems in science and engineering. Bayesian approximation and ensemble learning techniques are two widely-used types of uncertainty quantification (UQ) methods. In this regard, researchers have proposed different UQ methods and examined their performance in a variety of applications such as computer vision (e.g., self-driving cars and object detection), image processing (e.g., image restoration), medical image analysis (e.g., medical image classification and segmentation), natural language processing (e.g., text classification, social media texts and recidivism risk-scoring), bioinformatics, etc. This study reviews recent advances in UQ methods used in deep learning, investigates the application of these methods in reinforcement learning, and highlights fundamental research challenges and directions associated with UQ.

see all

Series: Information fusion
ISSN: 1566-2535
ISSN-E: 1872-6305
ISSN-L: 1566-2535
Volume: 76
Pages: 243 - 297
DOI: 10.1016/j.inffus.2021.05.008
Type of Publication: A1 Journal article – refereed
Field of Science: 113 Computer and information sciences
Copyright information: © 2021 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (