What is it about?
We introduce the topic of uncertainty estimation, and we analyze the peculiarities of such estimation when applied to classification systems. We analyze different methods that have been designed to provide classification systems based on deep learning with mechanisms for measuring the uncertainty of their predictions. We will take a look at how this uncertainty can be modeled and measured using different approaches, as well as practical considerations of different applications of uncertainty.
Featured Image
Photo by hao wang on Unsplash
Why is it important?
Decision-making based on machine learning systems is a subject of maximum interest in many application scenarios. It is, therefore, necessary to equip these systems with a means of estimating uncertainty in the predictions they emit in order to help users to make more informed decisions.
Perspectives
This survey aims at providing a pragmatic overview of the estimation of uncertainty in classification systems that can be very useful for both academic research and deep learning practitioners.
Jordi Vitrià
Universitat de Barcelona
Read the Original
This page is a summary of: A Survey on Uncertainty Estimation in Deep Learning Classification Systems from a Bayesian Perspective, ACM Computing Surveys, December 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3477140.
You can read the full text:
Contributors
The following have contributed to this page
