A review of uncertainty quantification in deep learning: Techniques, applications and challenges
Article
Abdar, Moloud, Pourpanah, Farhad, Hussain, Sadiq, Rezazadegan, Dana, Liu, Li, Ghavamzadeh, Mohammad, Fieguth, Paul, Cao, Xiaochun, Khosravi, Abbas, Acharya, U. Rajendra, Makarenkov, Vladimir and Nahavandi, S.. 2021. "A review of uncertainty quantification in deep learning: Techniques, applications and challenges." Information Fusion. 76, pp. 243-297. https://doi.org/10.1016/j.inffus.2021.05.008
Article Title | A review of uncertainty quantification in deep learning: Techniques, applications and challenges |
---|---|
ERA Journal ID | 20983 |
Article Category | Article |
Authors | Abdar, Moloud, Pourpanah, Farhad, Hussain, Sadiq, Rezazadegan, Dana, Liu, Li, Ghavamzadeh, Mohammad, Fieguth, Paul, Cao, Xiaochun, Khosravi, Abbas, Acharya, U. Rajendra, Makarenkov, Vladimir and Nahavandi, S. |
Journal Title | Information Fusion |
Journal Citation | 76, pp. 243-297 |
Number of Pages | 55 |
Year | 2021 |
Publisher | Elsevier |
Place of Publication | Netherlands |
ISSN | 1566-2535 |
1872-6305 | |
Digital Object Identifier (DOI) | https://doi.org/10.1016/j.inffus.2021.05.008 |
Web Address (URL) | https://www.sciencedirect.com/science/article/pii/S1566253521001081 |
Abstract | 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. |
Keywords | Artificial intelligence; Uncertainty quantification; Deep learning; Machine learning; Bayesian statistics; Ensemble learning |
ANZSRC Field of Research 2020 | 400306. Computational physiology |
Public Notes | Export Date: 9 October 2023 |
Byline Affiliations | Deakin University |
Shenzhen University, China | |
Dibrugarh University, India | |
Swinburne University of Technology | |
University of Oulu, Finland | |
Google, United States | |
University of Waterloo, Canada | |
Chinese Academy of Sciences, China | |
Ngee Ann Polytechnic, Singapore | |
Asia University, Taiwan | |
Singapore University of Social Sciences (SUSS), Singapore | |
University of Quebec, Canada |
Permalink -
https://research.usq.edu.au/item/z1v49/a-review-of-uncertainty-quantification-in-deep-learning-techniques-applications-and-challenges
Download files
51
total views46
total downloads1
views this month1
downloads this month