Johnson, Colin G. (2009) Genetic Programming Crossover: Does It Cross Over? In: EuroGP 2009: Genetic Programming. Lecture Notes in Computer Science . pp. 97-108. Springer, Heidelberg ISBN 978-3-642-01180-1. E-ISBN 978-3-642-01181-8. (doi:10.1007/978-3-642-01181-8_9) (KAR id:71019)
PDF
Author's Accepted Manuscript
Language: English |
|
Download this file (PDF/1MB) |
|
Request a format suitable for use with assistive technology e.g. a screenreader | |
Official URL: https://doi.org/10.1007/978-3-642-01181-8_9 |
Abstract
One justification for the use of crossover operators in Genetic Programming is that the crossover of program syntax gives rise to the crossover of information at the semantic level. In particular, a fitness-increasing crossover is presumed to act by combining fitness-contributing components of both parents. In this paper we investigate a particular interpretation of this hypothesis via an experimental study of 70 GP runs, in which we categorise each crossover event by its fitness properties and the information that contributes most strongly to those fitness properties. Some tentative evidence in support of the above hypothesis is extracted from this categorisation.
Item Type: | Conference or workshop item (Proceeding) |
---|---|
DOI/Identification number: | 10.1007/978-3-642-01181-8_9 |
Subjects: | Q Science > QA Mathematics (inc Computing science) > QA 76 Software, computer programming, |
Divisions: | Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing |
Depositing User: | Colin Johnson |
Date Deposited: | 14 Dec 2018 10:23 UTC |
Last Modified: | 05 Nov 2024 12:33 UTC |
Resource URI: | https://kar.kent.ac.uk/id/eprint/71019 (The current URI for this page, for reference purposes) |
- Link to SensusAccess
- Export to:
- RefWorks
- EPrints3 XML
- BibTeX
- CSV
- Depositors only (login required):