Table of Contents

1 Introduction.- 2 Fitness Landscapes.- 3 Program Component Schema Theories.- 4 Pessimistic GP Schema Theories.- 5 Exact GP Schema Theorems.- 6 Lessons from the GP Schema Theory.- 7 The Genetic Programming Search Space.- The GP Search Space: Theoretical Analysis.- 9 Example I: The Artificial Ant.- 10 Example II: The Max Problem.- 11 GP Convergence and Bloat.- 12 Conclusions.- A Genetic Programming Resources.- List of Special Symbols.

Reviews

From the reviews: I came to this book from an engineering perspective as a GP practitioner
interested in practical issues such as which cross-over operator was most
applicable for my problem. Whilst this book did not offer any clear-cut
answers, this is a reflection of the fact that there are no clear-cut answers,
yet. What the book does succeed in doing is providing an illuminating overview
of the body of work which will, in time, come to provide a theoretical
foundation, and accurate prescriptions, for all of the ad-hoc tweaks and
adjustments that we make in practise.
This was published in the British Computer Society journal "Expert Update", 5(3) p46, 2002 by Steve Phelps. "Is genetic programming (GP) better than random search? … Langdon and Poli take on the ambitious task of giving a unified overview of a field still in its infancy, and the result is an invaluable companion to the literature. The book … proceeds to give a comprehensive and illuminating treatment of the most important theorems. … throughout the book the formal side of the theory is developed alongside intuitive explanations and constructive analysis of actual empirical data." (Steve Phelps, Expert Update, Vol. 5 (3), 2002) "The book ‘Foundations of Genetics Programming’ summarizes appearances and approaches in the GP section. … There are many references for details in the text. Naturally, a large list of references is printed in the appendix. In conclusion, the book describes general principles of genetic programming. I recommend this as the first book for those who are familiarized with the GA and want to be in the know of the GP." (Vít Fábera, Neural Network World, Vol. 12 (4), 2002)