A comparative study of an evolvability indicator and a predictor of expected performance for genetic programming

Published in Conferences Papers
  1. Leonardo Trujillo, Yuliana Mart\'ınez, Edgar Galván López and Pierrick Legrand. A comparative study of an evolvability indicator and a predictor of expected performance for genetic programming. In GECCO (Companion). 2012, 1489-1490. BibTeX

    @inproceedings{DBLP:conf/gecco/TrujilloMLL12,
    	author = "Leonardo Trujillo and Yuliana Mart\'{\i}nez and Edgar Galv{\'a}n L{\'o}pez and Pierrick Legrand",
    	title = "A comparative study of an evolvability indicator and a predictor of expected performance for genetic programming",
    	booktitle = "GECCO (Companion)",
    	year = 2012,
    	pages = "1489-1490",
    	ee = "http://doi.acm.org/10.1145/2330784.2331006",
    	crossref = "DBLP:conf/gecco/2012c",
    	bibsource = "DBLP, http://dblp.uni-trier.de"
    }
    
  2. Terence Soule and Jason H Moore (eds.). Genetic and Evolutionary Computation Conference, GECCO '12, Philadelphia, PA, USA, July 7-11, 2012, Companion Material Proceedings. ACM, 2012. BibTeX

    @proceedings{DBLP:conf/gecco/2012c,
    	editor = "Terence Soule and Jason H. Moore",
    	title = "Genetic and Evolutionary Computation Conference, GECCO '12, Philadelphia, PA, USA, July 7-11, 2012, Companion Material Proceedings",
    	booktitle = "GECCO (Companion)",
    	publisher = "ACM",
    	year = 2012,
    	isbn = "978-1-4503-1178-6",
    	ee = "http://dl.acm.org/citation.cfm?id=2330784",
    	bibsource = "DBLP, http://dblp.uni-trier.de"
    }
    
Abstract

An open question within Genetic Programming (GP) is how to characterize problemdifficulty. The goal is to develop predictive tools that estimate how difficult a problemis for GP to solve. Here we consider two groups of methods. We call the first group Evolvability Indicators (EI), measures that capture how amendable the fitness landscape is to a GP search. Examples of EIs are Fitness Distance Correlation (FDC) and Negative Slope Coefficient (NSC). The second group are Predictors of Expected Performance (PEP), models that take as input a set of descriptive attributes of a problem and predict the expected performance of GP. This paper compares an EI, the NSC, and a PEP model for a GP classifier. Results suggest that the EI does not correlate with the performance of the GP classifiers. Conversely, the PEP models show a high correlation with GP performance.

Published in
GECCO Companion '12 Proceedings of the fourteenth international conference on Genetic and evolutionary computation conference companion
Pages 1489-1490
http://dl.acm.org/citation.cfm?id=2331006
Date of conference
07 - 11 July 2012
ISBN
978-1-4503-1178-6
Feedback