Contents

• List of Figures
• List of Tables
• 1 An Analysis of Diversity
  • 1 Introduction
  • 2 Research Perspective
  • 3 Contributions
  • 4 Overview
  
  
• 2 Search, Evolutionary Algorithms and Genetic Programming
  • 1 Problem Solving and Search
    • 1 Requirements of Search
    • 2 Algorithms to Perform Search
  • 2 Evolutionary Algorithms
  • 3 Genetic Programming
    • 1 Foundations
    • 2 The Genetic Programming Algorithm
    • 3 Representation of Solutions
    • 4 Initialisation
    • 5 Fitness and Selection
    • 6 Recombination, Mutation and Reproduction
    • 7 Stopping Criterion
  • 4 Application Domains
    • 1 Artificial Ant
    • 2 Even Parity
    • 3 Symbolic Regression
  • 5 Scalability and Fitness Landscape
  • 6 Metaphors of Search
  • 7 Summary
  
  
• 3 Issues in Genetic Programming
  • 1 Diversity Measures and Methods
    • 1 Measuring Diversity
    • 2 Controlling Diversity
  • 2 The Effects of Population Diversity
    • 1 Code Growth
    • 2 Problem Difficulty
    • 3 Selection Pressure and Deception
  • 3 The Role of the Population
    • 1 Local or Global Search
    • 2 Representation and Operator Conflicts
  • 4 Summary
  
  
• 4 Analysis of Diversity Measures
  • 1 Diversity Measures
    • 1 Promoting Diversity
  • 2 Empirical Analysis of Diversity Measures
    • 1 Diversity Measures Used
    • 2 Correlation Measures
  • 3 Analysis of Results
    • 1 Correlations in Final Populations
    • 2 Evolving Populations' Correlation
    • 3 Scatter Plots of Diversity and Fitness
  • 4 Discussion of Diversity Measures
  • 5 Summary
  
  
• 5 Genetic Lineages and A Metaphor of Hill Climbing
  • 1 Genetic Lineages
    • 1 A Caricature of Tournament Selection
    • 2 Variation of Loss of Lineages
    • 3 Relevance to the Fitness Landscape
  • 2 Experimental Study using Lineage Selection
    • 1 Lineage Selection
    • 2 Other Forms of Lineage Selection
  • 3 Results of Lineage Selection
  • 4 Discussion of the Metaphor of Hill Climbing
    • 1 Artificial Ant
    • 2 Parity
    • 3 Binomial-3
    • 4 Remarks
  • 5 Sampling of Unique Structures and Behaviours
    • 1 Problems and Measures
  • 6 Analysis of Results
  • 7 Discussion of Sampling
  • 8 Summary
  
  
• 6 Effects of Population Diversity: Code Growth and Problem Difficulty
  • 1 Code Growth and Problem Difficulty
  • 2 Regression Problems and Increased Difficulty
    • 1 Population Measures: Entropy and Edit Distance Diversity
  • 3 Experimental Investigation
  • 4 Binomial-3 and Random Polynomial Results
    • 1 Establishing Difficulty
    • 2 Binomial-3 Results
    • 3 Random Polynomials
  • 5 Discussion of a Causal Model
    • 1 Hypothesis
    • 2 A Model of Difficulty
    • 3 Recommendations
  • 6 Summary
  
  
• 7 Diversity, Survivability and a Niche for Island Models
  • 1 Previous Distributed Evolution Work
    • 1 Evolutionary and Genetic Algorithm Models
    • 2 Genetic Programming Distributed Models
    • 3 Speciation, Niching and Other Methods
    • 4 Biological Foundations of Distributed Models
    • 5 Comments on Previous Distributed Models
  • 2 Survivability of the Diverse
  • 3 Genetic Outliers and Survivability
    • 1 The Tree-String Problem
    • 2 Relevance to Other Domains
    • 3 Experimental Details
    • 4 Genetic Outlier Definition
    • 5 Genetic Properties Contributing to the Evolutionary Process
    • 6 Alternative Definitions
    • 7 Discussion of Experimental Results
  • 4 The Ant, Parity and Regression Domains
  • 5 A Niche for Island Models in Genetic Programming
    • 1 Proposed Niche Solution
    • 2 Similar Models
    • 3 The Island, Post-Speciation Event and Other Comments
  • 6 Summary
  
  
• 8 Conclusions
  • 1 Contributions
    • 1 A survey and analysis of diversity in genetic programming demonstrated the complexity behind the issue of diversity measures and methods and the relationship between diversity and fitness.
    • 2 An analysis using genetic lineages showed how a search metaphor of hill-climbing can be used to explain and improve genetic programming search. Also, the sampling of unique structures and behaviours demonstrated the the low sampling of both complex behaviours and unique structures of large size.
    • 3 A causal model was developed which linked increased rates of code growth to non-decreased selection pressure and to increased similarity within the population. Decreased selection pressure occurs when fitness-based diversity is lost, and increased similarity in the population is the result of both faster convergence and non-decreased selection pressure.
    • 4 An analysis using the Tree-String problem showed the inability to produce good offspring by both dissimilar-and-fit individuals and by similar-and-equally-well-fit individuals.
    • 5 A model was proposed that identifies dissimilar individuals and moves them to new islands where they can contribute to search more effectively.
    • 6 Summary
  • 2 Remarks and Problem Specific Conclusions
    • 1 Ant Remarks
    • 2 Parity Remarks
    • 3 Regression Remarks
  • 3 Future Directions
    • 1 Diversity Measures and Methods
    • 2 Code Growth and Problem Difficulty
    • 3 Defining the Role of the Populations
    • 4 Extended Metaphors of Search
  
  
• Bibliography
• About this document ...