Skip to main content
Article
A Guide for Fitness Function Design
Proceedings of the 13th Annual Genetic and Evolutionary Computation Conference, GECCO'11
  • Josh L. Wilkerson
  • Daniel R. Tauritz, Missouri University of Science and Technology
Abstract

Fitness function design is often both a design and performance bottleneck for evolutionary algorithms. The fitness function for a given problem is directly related to the specifications for that problem. This paper outlines a guide for transforming problem specifications into a fitness function. The target audience for this guide are both non-expert practitioners and those interested in formalizing fitness function design. The goal is to investigate and formalize the fitness function generation process that expert developers go through and in doing so make fitness function design less of a bottleneck. Solution requirements in the problem specifications are identified and classified, then an appropriate fitness function component is generated based on its classifications, and finally the fitness function components combined to yield a fitness function for the problem in question. The competitive performance of a guide generated fitness function is demonstrated by comparing it to that of an expert designed fitness function.

Meeting Name
13th Annual Genetic and Evolutionary Computation Conference, GECCO'11 (2011: Jul. 12-16, Dublin, Ireland)
Department(s)
Computer Science
Sponsor(s)
Missouri University of Science and Technology. Natural Computation Laboratory
Keywords and Phrases
  • Evolutionary Algorithm,
  • Fitness Function Classification,
  • Fitness Function Design
International Standard Book Number (ISBN)
9781450306904
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2011 Association for Computing Machinery (ACM), All rights reserved.
Publication Date
1-1-2011
Disciplines
Citation Information
Josh L. Wilkerson and Daniel R. Tauritz. "A Guide for Fitness Function Design" Proceedings of the 13th Annual Genetic and Evolutionary Computation Conference, GECCO'11 (2011) p. 123 - 124
Available at: http://works.bepress.com/daniel-tauritz/2/