Handling Uncertainty in Artificial Intelligence (SpringerBriefs in Applied Sciences and Technology)

✍ Scribed by Jyotismita Chaki

• Publisher: Springer
• Year: 2023
• Tongue: English
• Leaves: 111
• Category: Library

✦ Synopsis

This book demonstrates different methods (as well as real-life examples) of handling uncertainty like probability and Bayesian theory, Dempster-Shafer theory, certainty factor and evidential reasoning, fuzzy logic-based approach, utility theory and expected utility theory. At the end, highlights will be on the use of these methods which can help to make decisions under uncertain situations. This book assists scholars and students who might like to learn about this area as well as others who may have begun without a formal presentation. The book is comprehensive, but it prohibits unnecessary mathematics.

✦ Table of Contents

Preface
Contents
About the Author
1 Introduction to Handling Uncertainty in Artificial Intelligence
1.1 Introduction
1.2 Common Challenges of Handling Uncertainty in Artificial Intelligence
1.3 Numeric Approaches
1.3.1 Probability and Bayesian Theory
1.3.2 The Dempster–Shafer Theory
1.3.3 Certainty Factor and Evidential Reasoning
1.3.4 Fuzzy Logic-Based Approach
1.4 Symbolic Approaches
1.4.1 Non-monotonic Approach
1.4.2 Cohen’s Theory of Endorsements
1.5 Summary
References
2 Probability and Bayesian Theory to Handle Uncertainty in Artificial Intelligence
2.1 Introduction
2.2 Popular Phrases Related to Probability
2.2.1 Event
2.2.2 Sample Space
2.2.3 Random Variables
2.3 Ways to Solve Uncertainty Using Probability
2.3.1 Bayes’ Theorem
2.3.2 Bayesian Belief Network
2.4 Advantages of Probability-Based Methods
2.5 Limitations of Probability-Based Methods
2.6 Summary
References
3 The Dempster–Shafer Theory to Handle Uncertainty in Artificial Intelligence
3.1 Introduction
3.2 Basic Terms Used in D-S Theory
3.2.1 Frame of Discernment (Φ)
3.2.2 Power Set P(φ) = 2φ
3.2.3 Evidence
3.2.4 Data Source
3.2.5 Data Fusion
3.3 Main Components of D-S Theory
3.3.1 Basic Probability Assignment (BPA) or Mass Function (M-value)
3.3.2 Belief Function (Bel)
3.3.3 Plausibility Function (Pl)
3.3.4 Commonality Function C (Q)
3.3.5 Uncertainty Interval (U)
3.4 D-S Rule of Combination
3.5 Advantages of D-S Theory
3.6 Limitations of D-S Theory
3.7 Summary
References
4 Certainty Factor and Evidential Reasoning to Handle Uncertainty in Artificial Intelligence
4.1 Introduction
4.2 Case Study 1
4.3 Case Study 2
4.4 Case Study 3
4.5 Advantages of CF
4.6 Limitations of CF
4.7 Summary
References
5 A Fuzzy Logic-Based Approach to Handle Uncertainty in Artificial Intelligence
5.1 Introduction
5.2 Characteristics of Fuzzy Logic
5.3 Fuzzy Logic Versus Probability
5.4 Membership Functions
5.4.1 Singleton Membership Function
5.4.2 Triangular Membership Function
5.4.3 Trapezoidal Membership Function
5.4.4 Gaussian Membership Function
5.4.5 Generalized Bell-Shaped Membership Function
5.5 Architecture of the Fuzzy Logic-Based System
5.5.1 Rule Base
5.5.2 Fuzzification
5.5.3 Inference Engine
5.5.4 Defuzzification
5.6 Case Study
5.7 Advantages of Fuzzy Logic System
5.8 Limitations of Fuzzy Logic Systems
5.9 Summary
References
6 Decision-Making Under Uncertainty in Artificial Intelligence
6.1 Introduction
6.2 Types of Decisions
6.2.1 Strategic Decision
6.2.2 Administrative Decision
6.2.3 Operating Decision
6.3 Steps in Decision-Making
6.4 Criterion for Deciding Under Uncertainty
6.4.1 Maximax
6.4.2 Maximin
6.4.3 Minimax Regret
6.4.4 Hurwicz Criteria
6.4.5 Laplace Criteria
6.5 Utility Theory
6.5.1 Utility Functions
6.5.2 Expected Utility
6.6 Decision Network
6.6.1 Solving the Weakness Decision Network—Enumerating All Policies
6.6.2 Solving the Weakness Decision Network—Variable Elimination Algorithm
6.7 Applying the Variable Elimination Algorithm to a Therapeutic Diagnostic Scenario
6.8 Advantages of Expected Utility Under an Uncertain Situation
6.9 Limitations of Expected Utility Under an Uncertain Situation
6.10 Summary
References
7 Applications of Different Methods to Handle Uncertainty in Artificial Intelligence
7.1 Applications of Probability and Bayesian Theory in the Field of Uncertainty
7.2 Applications of Dempster–Shafer (DS) Theory in the Field of Uncertainty
7.3 Applications of Certainty Factor (CF) in the Field of Uncertainty
7.4 Applications of Fuzzy Logic in the Field of Uncertainty
7.5 Applications of Utility and Expected Utility Theory
7.6 Summary
References