A Survey on Uncertainty Reasoning and Quantification for Decision Making: Belief Theory Meets Deep Learning

06/12/2022
by   Zhen Guo, et al.
41

An in-depth understanding of uncertainty is the first step to making effective decisions under uncertainty. Deep/machine learning (ML/DL) has been hugely leveraged to solve complex problems involved with processing high-dimensional data. However, reasoning and quantifying different types of uncertainties to achieve effective decision-making have been much less explored in ML/DL than in other Artificial Intelligence (AI) domains. In particular, belief/evidence theories have been studied in KRR since the 1960s to reason and measure uncertainties to enhance decision-making effectiveness. We found that only a few studies have leveraged the mature uncertainty research in belief/evidence theories in ML/DL to tackle complex problems under different types of uncertainty. In this survey paper, we discuss several popular belief theories and their core ideas dealing with uncertainty causes and types and quantifying them, along with the discussions of their applicability in ML/DL. In addition, we discuss three main approaches that leverage belief theories in Deep Neural Networks (DNNs), including Evidential DNNs, Fuzzy DNNs, and Rough DNNs, in terms of their uncertainty causes, types, and quantification methods along with their applicability in diverse problem domains. Based on our in-depth survey, we discuss insights, lessons learned, limitations of the current state-of-the-art bridging belief theories and ML/DL, and finally, future research directions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/27/2022

Quantification of Deep Neural Network Prediction Uncertainties for VVUQ of Machine Learning Models

Recent performance breakthroughs in Artificial intelligence (AI) and Mac...
research
04/20/2023

Multidimensional Uncertainty Quantification for Deep Neural Networks

Deep neural networks (DNNs) have received tremendous attention and achie...
research
08/19/2020

A Survey of Knowledge-based Sequential Decision Making under Uncertainty

Reasoning with declarative knowledge (RDK) and sequential decision-makin...
research
10/25/2022

UNIFY: a Unified Policy Designing Framework for Solving Constrained Optimization Problems with Machine Learning

The interplay between Machine Learning (ML) and Constrained Optimization...
research
05/22/2022

Analysis of functional neural codes of deep learning models

Deep neural networks (DNNs), the agents of deep learning (DL), require a...
research
09/14/2023

Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance

In real-world scenarios, typical visual recognition systems could fail u...
research
12/13/2022

An Exploratory Study of AI System Risk Assessment from the Lens of Data Distribution and Uncertainty

Deep learning (DL) has become a driving force and has been widely adopte...

Please sign up or login with your details

Forgot password? Click here to reset