Controlling Individuals Growth in Semantic Genetic Programming through Elitist Replacement
Joint Authors
Castelli, Mauro
Vanneschi, Leonardo
Popovič, Aleš
Source
Computational Intelligence and Neuroscience
Issue
Vol. 2016, Issue 2016 (31 Dec. 2015), pp.1-12, 12 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2015-12-27
Country of Publication
Egypt
No. of Pages
12
Main Subjects
Abstract EN
In 2012, Moraglio and coauthors introduced new genetic operators for Genetic Programming, called geometric semantic genetic operators.
They have the very interesting advantage of inducing a unimodal error surface for any supervised learning problem.
At the same time, they have the important drawback of generating very large data models that are usually very hard to understand and interpret.
The objective of this work is to alleviate this drawback, still maintaining the advantage.
More in particular, we propose an elitist version of geometric semantic operators, in which offspring are accepted in the new population only if they have better fitness than their parents.
We present experimental evidence, on five complex real-life test problems, that this simple idea allows us to obtain results of a comparable quality (in terms of fitness), but with much smaller data models, compared to the standard geometric semantic operators.
In the final part of the paper, we also explain the reason why we consider this a significant improvement, showing that the proposed elitist operators generate manageable models, while the models generated by the standard operators are so large in size that they can be considered unmanageable.
American Psychological Association (APA)
Castelli, Mauro& Vanneschi, Leonardo& Popovič, Aleš. 2015. Controlling Individuals Growth in Semantic Genetic Programming through Elitist Replacement. Computational Intelligence and Neuroscience،Vol. 2016, no. 2016, pp.1-12.
https://search.emarefa.net/detail/BIM-1099789
Modern Language Association (MLA)
Castelli, Mauro…[et al.]. Controlling Individuals Growth in Semantic Genetic Programming through Elitist Replacement. Computational Intelligence and Neuroscience Vol. 2016, no. 2016 (2015), pp.1-12.
https://search.emarefa.net/detail/BIM-1099789
American Medical Association (AMA)
Castelli, Mauro& Vanneschi, Leonardo& Popovič, Aleš. Controlling Individuals Growth in Semantic Genetic Programming through Elitist Replacement. Computational Intelligence and Neuroscience. 2015. Vol. 2016, no. 2016, pp.1-12.
https://search.emarefa.net/detail/BIM-1099789
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1099789