[Review] "...a major contribution to the evolutionary computation literature...recommended reading for experienced researchers, as well as novice students…" (Computing Reviews.com, May 26, 2006)
[Book Description]
This Third Edition provides the latest tools and techniques that enable computers to learn
The Third Edition of this internationally acclaimed publication provides the latest theory and techniques for using simulated evolution to achieve machine intelligence. As a leading advocate for evolutionary computation, the author has successfully challenged the traditional notion of artificial intelligence, which essentially programs human knowledge fact by fact, but does not have the capacity to learn or adapt as evolutionary computation does.
Readers gain an understanding of the history of evolutionary computation, which provides a foundation for the author's thorough presentation of the latest theories shaping current research. Balancing theory with practice, the author provides readers with the skills they need to apply evolutionary algorithms that can solve many of today's intransigent problems by adapting to new challenges and learning from experience. Several examples are provided that demonstrate how these evolutionary algorithms learn to solve problems. In particular, the author provides a detailed example of how an algorithm is used to evolve strategies for playing chess and checkers.
As readers progress through the publication, they gain an increasing appreciation and understanding of the relationship between learning and intelligence. Readers familiar with the previous editions will discover much new and revised material that brings the publication thoroughly up to date with the latest research, including the latest theories and empirical properties of evolutionary computation.
The Third Edition also features new knowledge-building aids. Readers will find a host of new and revised examples. New questions at the end of each chapter enable readers to test their knowledge. Intriguing assignments that prepare readers to manage challenges in industry and research have been added to the end of each chapter as well.
This is a must-have reference for professionals in computer and electrical engineering; it provides them with the very latest techniques and applications in machine intelligence. With its question sets and assignments, the publication is also recommended as a graduate-level textbook.
Table Of Contents

Preface to the Third Edition

Preface to the Second Edition

Preface to the First Edition

             Defining Artificial Intelligence

                    Background

                    The Turing Test

                    Simulation of Human Expertise

                           Samuel's Checker Program

                           Chess Programs

                           Expert Systems

                           A Criticism of the Expert Systems or Knowledge-Based Approach

                           Fuzzy Systems

                           Perspective on Methods Employing Specific Heuristics

                    Neural Networks

                    Definition of Intelligence

                    Intelligence, the Scientific Method, and Evolution

                    Evolving Artificial Intelligence

                           References

                           Chapter 1 Exercises

             Natural Evolution

                    The Neo-Darwinian Paradigm

                    The Genotype and the Phenotype: The Optimization of Behavior

                    Implications of Wright's Adaptive Topography: Optimization Is Extensive Yet Incomplete

                    The Evolution of Complexity: Minimizing Surprise

                    Sexual Reproduction

                    Sexual Selection

                    Assessing the Beneficiary of Evoluationary Optimization

                    Challenges to Neo-Darwinism

                           Neutral Mutations and the Neo-Darwinian Paradigm

                           Punctuated Equilibrium

                    Summary

                           References

                           Chapter 2 Exercises

             Computer Simulation of Natural Evolution

                    Early Speculations and Specific Attempts

                           Evolutionary Operation

                           A Learning Machine

                    Artificial Life

                    Evolutionary Programming

                    Evolution Strategies

                    Genetic Algorithms

                    The Evolution of Evolutionary Computation

                           References

                           Chapter 3 Exercises

             Theoretical and Empirical Properties of Evolutionary Computation

                    The Challenge

                    Theoretical Analysis of Evolutionary Computation

                           The Framework for Analysis

                           Convergence in the Limit

                           The Error of Minimizing Expected Losses in Schema Processing

                           The Two-Armed Bandit Problem

                           Extending the Analysis for ``Optimally'' Allocating Trials

                           Limitations of the Analysis

                           Misallocating Trials and the Schema Theorem in the Presence of Noise

                           Analyzing Selection

                           Convergence Rates for Evolutionary Algorithms

                           Does a Best Evolutionary Algorithm Exist?

                    Empirical Analysis

                           Variations of Crossover

                           Dynamic Parameter Encoding

                           Comparing Crossover to Mutation

                           Crossover as a Macromutation

                           Self-Adaptation in Evolutionary Algorithms

                           Fitness Distributions of Search Operators

                    Discussion

                           References

                           Chapter 4 Exercises

             Intelligent Behavior

                    Intelligence in Static and Dynamic Environments

                    General Problem Solving: Experiments with Tic-Tac-Toe

                    The Prisoner's Dilemma: Coevolutionary Adaptation

                           Background

                           Evolving Finite-State Representations

                    Learning How to Play Checkers without Relying on Expert Knowledge

                    Evolving a Self-Learning Chess Player

                    Discussion

                           References

                           Chapter 5 Exercises

             Perspective

                    Evolution as a Unifying Principle of Intelligence

                    Prediction and the Languagelike Nature of Intelligence

                    The Misplaced Emphasis on Emulating Genetic Mechanisms

                    Bottom-Up Versus Top-Down

                    Toward a New Philosophy of Machine Intelligence

                           References

                           Chapter 6 Exercises

Glossary

Index

About the Author