| |
| |
| |
Introduction | |
| |
| |
| |
Basic Evolutionary Processes | |
| |
| |
| |
EV: A Simple Evolutionary System | |
| |
| |
| |
EV on a Simple Fitness Landscape | |
| |
| |
| |
EV on a More Complex Fitness Landscape | |
| |
| |
| |
Evolutionary Systems as Problem Solvers | |
| |
| |
| |
Exercises | |
| |
| |
| |
A Historical Perspective | |
| |
| |
| |
Early Algorithmic Views | |
| |
| |
| |
The Catalytic 1960s | |
| |
| |
| |
The Explorative 1970s | |
| |
| |
| |
Evolutionary Programming | |
| |
| |
| |
Evolution Strategies | |
| |
| |
| |
Genetic Algorithms | |
| |
| |
| |
The Exploitative 1980s | |
| |
| |
| |
Optimization Applications | |
| |
| |
| |
Other EA Applications | |
| |
| |
| |
Summary | |
| |
| |
| |
The Unifying 1990s | |
| |
| |
| |
The Twenty-first Century: Mature Expansion | |
| |
| |
| |
Summary | |
| |
| |
| |
Canonical Evolutionary Algorithms | |
| |
| |
| |
Introduction | |
| |
| |
| |
EV(m,n) | |
| |
| |
| |
Evolutionary Programming | |
| |
| |
| |
Evolution Strategies | |
| |
| |
| |
Genetic Algorithms | |
| |
| |
| |
Multi-parent Reproduction | |
| |
| |
| |
Universal Genetic Codes | |
| |
| |
| |
Summary | |
| |
| |
| |
A Unified View of Simple EAs | |
| |
| |
| |
A Common Framework | |
| |
| |
| |
Population Size | |
| |
| |
| |
Parent Population Size m | |
| |
| |
| |
Offspring Population Size n | |
| |
| |
| |
Selection | |
| |
| |
| |
Choosing Selection Mechanisms | |
| |
| |
| |
Survival Selection: A Special Case | |
| |
| |
| |
Selection Summary | |
| |
| |
| |
Reproductive Mechanisms | |
| |
| |
| |
Mutation | |
| |
| |
| |
Recombination | |
| |
| |
| |
Crossover or Mutation? | |
| |
| |
| |
Representation Issues | |
| |
| |
| |
Choosing Effective Reproductive Mechanisms | |
| |
| |
| |
Summary | |
| |
| |
| |
Evolutionary Algorithms as Problem Solvers | |
| |
| |
| |
Simple EAs as Parallel Adaptive Search | |
| |
| |
| |
Representation | |
| |
| |
| |
Fixed-Length Linear Objects | |
| |
| |
| |
Nonlinear Objects | |
| |
| |
| |
Variable-Length Objects | |
| |
| |
| |
Nonlinear, Variable-Length Objects | |
| |
| |
| |
Reproductive Operators | |
| |
| |
| |
Objective Fitness Evaluation | |
| |
| |
| |
Population Sizes and Dynamics | |
| |
| |
| |
Convergence and Stopping Criteria | |
| |
| |
| |
Returning an Answer | |
| |
| |
| |
Summary | |
| |
| |
| |
EA-based Optimization | |
| |
| |
| |
OPT-EAs | |
| |
| |
| |
Fitness Scaling | |
| |
| |
| |
Convergence and Elitism | |
| |
| |
| |
Summary | |
| |
| |
| |
Parameter Optimization | |
| |
| |
| |
Phenotypic Representations and Operators | |
| |
| |
| |
Genotypic Representations and Operators | |
| |
| |
| |
Choosing Representations and Operators | |
| |
| |
| |
Real-Valued Parameter Optimization | |
| |
| |
| |
Integer-Valued Parameter Optimization | |
| |
| |
| |
Symbolic Parameter Optimization | |
| |
| |
| |
Non-homogeneous Parameter Optimization | |
| |
| |
| |
Constrained Optimization | |
| |
| |
| |
Data Structure Optimization | |
| |
| |
| |
Variable-Length Data Structures | |
| |
| |
| |
Multi-objective Optimization | |
| |
| |
| |
Summary | |
| |
| |
| |
EA-Based Search | |
| |
| |
| |
EA-Based Machine Learning | |
| |
| |
| |
EA-Based Automated Programming | |
| |
| |
| |
Representing Programs | |
| |
| |
| |
Evaluating Programs | |
| |
| |
| |
Summary | |
| |
| |
| |
EA-Based Adaptation | |
| |
| |
| |
Summary | |
| |
| |
| |
Evolutionary Computation Theory | |
| |
| |
| |
Introduction | |
| |
| |
| |
Analyzing EA Dynamics | |
| |
| |
| |
Selection-Only Models | |
| |
| |
| |
Non-overlapping-Generation Models | |
| |
| |
| |
Uniform (Neutral) Selection | |
| |
| |
| |
Fitness-Biased Selection | |
| |
| |
| |
Non-overlapping-Generation Models with n [not equal] m | |
| |
| |
| |
Overlapping-Generation Models | |
| |
| |
| |
Uniform (Neutral) Selection | |
| |
| |
| |
Fitness-Biased Selection | |
| |
| |
| |
Selection in Standard EAs | |
| |
| |
| |
Reducing Selection Sampling Variance | |
| |
| |
| |
Selection Summary | |
| |
| |
| |
Reproduction-Only Models | |
| |
| |
| |
Non-overlapping-Generation Models | |
| |
| |
| |
Reproduction for Fixed-Length Discrete Linear Genomes | |
| |
| |
| |
Reproduction for Other Genome Types | |
| |
| |
| |
Overlapping-Generation Models | |
| |
| |
| |
Reproduction Summary | |
| |
| |
| |
Selection and Reproduction Interactions | |
| |
| |
| |
Evolvability and Price's Theorem | |
| |
| |
| |
Selection and Discrete Recombination | |
| |
| |
| |
Discrete Recombination from a Schema Perspective | |
| |
| |
| |
Crossover-Induced Diversity | |
| |
| |
| |
Crossover-Induced Fitness Improvements | |
| |
| |
| |
Selection and Other Recombination Operators | |
| |
| |
| |
Selection and Mutation | |
| |
| |
| |
Mutation from a Schema Perspective | |
| |
| |
| |
Mutation-Induced Diversity | |
| |
| |
| |
Mutation-Induced Fitness Improvements | |
| |
| |
| |
Selection and Other Mutation Operators | |
| |
| |
| |
Selection and Multiple Reproductive Operators | |
| |
| |
| |
Selection, Reproduction, and Population Size | |
| |
| |
| |
Non-overlapping-Generation Models | |
| |
| |
| |
Overlapping-Generation Models | |
| |
| |
| |
Summary | |
| |
| |
| |
Representation | |
| |
| |
| |
Capturing Important Application Features | |
| |
| |
| |
Defining Effective Reproduction Operators | |
| |
| |
| |
Effective Mutation Operators | |
| |
| |
| |
Effective Recombination Operators | |
| |
| |
| |
Landscape Analysis | |
| |
| |
| |
Models of Canonical EAs | |
| |
| |
| |
Infinite Population Models for Simple GAs | |
| |
| |
| |
Expected Value Models of Simple GAs | |
| |
| |
| |
GA Schema Theory | |
| |
| |
| |
Summary | |
| |
| |
| |
Markov Models | |
| |
| |
| |
Markov Models of Finite Population EAs | |
| |
| |
| |
Markov Models of Simple GAs | |
| |
| |
| |
Summary | |
| |
| |
| |
Statistical Mechanics Models | |
| |
| |
| |
Summary | |
| |
| |
| |
Application-Oriented Theories | |
| |
| |
| |
Optimization-Oriented Theories | |
| |
| |
| |
Convergence and Rates of Convergence | |
| |
| |
| |
ESs and Real-Valued Parameter Optimization Problems | |
| |
| |
| |
Simple EAs and Discrete Optimization Problems | |
| |
| |
| |
Optimizing with Genetic Algorithms | |
| |
| |
| |
Summary | |
| |
| |
| |
Advanced EC Topics | |
| |
| |
| |
Self-adapting EAs | |
| |
| |
| |
Adaptation at EA Design Time | |
| |
| |
| |
Adaptation over Multiple EA Runs | |
| |
| |
| |
Adaptation during an EA Run | |
| |
| |
| |
Summary | |
| |
| |
| |
Dynamic Landscapes | |
| |
| |
| |
Standard EAs on Dynamic Landscapes | |
| |
| |
| |
Modified EAs for Dynamic Landscapes | |
| |
| |
| |
Categorizing Dynamic Landscapes | |
| |
| |
| |
The Importance of the Rate of Change | |
| |
| |
| |
The Importance of Diversity | |
| |
| |
| |
Summary | |
| |
| |
| |
Exploiting Parallelism | |
| |
| |
| |
Coarse-Grained Parallel EAs | |
| |
| |
| |
Fine-Grained Models | |
| |
| |
| |
Summary | |
| |
| |
| |
Evolving Executable Objects | |
| |
| |
| |
Representation of Behaviors | |
| |
| |
| |
Summary | |
| |
| |
| |
Multi-objective EAs | |
| |
| |
| |
Hybrid EAs | |
| |
| |
| |
Biologically Inspired Extensions | |
| |
| |
| |
Non-random Mating and Speciation | |
| |
| |
| |
Coevolutionary Systems | |
| |
| |
| |
CoEC Architectures | |
| |
| |
| |
CoEC Dynamics | |
| |
| |
| |
Generative Representations and Morphogenesis | |
| |
| |
| |
Inclusion of Lamarckian Properties | |
| |
| |
| |
Agent-Oriented Models | |
| |
| |
| |
Summary | |
| |
| |
| |
Summary | |
| |
| |
| |
The Road Ahead | |
| |
| |
| |
Modeling General Evolutionary Systems | |
| |
| |
| |
More Unification | |
| |
| |
| |
Summary | |
| |
| |
| |
Source Code Overview | |
| |
| |
| |
EC1: A Very Simple EC System | |
| |
| |
| |
EC1 Code Structure | |
| |
| |
| |
EC1 Parameters | |
| |
| |
| |
EC2: A More Interesting EC System | |
| |
| |
| |
EC3: A More Flexible EC System | |
| |
| |
| |
EC4: An EC Research System | |
| |
| |
Bibliography | |
| |
| |
Index | |