- author = "Leonardo Vanneschi and Steven Gustafson",
- title = "Using crossover based similarity measure to improve genetic programming generalization ability",
- booktitle = "GECCO '09: Proceedings of the 11th Annual conference on Genetic and evolutionary computation",
- year = "2009",
- editor = "Guenther Raidl and Franz Rothlauf and Giovanni Squillero and Rolf Drechsler and Thomas Stuetzle and Mauro Birattari and Clare Bates Congdon and Martin Middendorf and Christian Blum and Carlos Cotta and Peter Bosman and Joern Grahl and Joshua Knowles and David Corne and Hans-Georg Beyer and Ken Stanley and Julian F. Miller and Jano {van Hemert} and Tom Lenaerts and Marc Ebner and Jaume Bacardit and Michael O'Neill and Massimiliano {Di Penta} and Benjamin Doerr and Thomas Jansen and Riccardo Poli and Enrique Alba",
- pages = "1139--1146",
- address = "Montreal",
- publisher = "ACM",
- publisher_address = "New York, NY, USA",
- month = "8-12 " # jul,
- organisation = "SigEvo",
- keywords = "genetic algorithms, genetic programming",
- isbn13 = "978-1-60558-325-9",
- bibsource = "DBLP, http://dblp.uni-trier.de",
-
DOI = "
doi:10.1145/1569901.1570054",
- abstract = "Generalization is a very important issue in Machine Learning. In this paper, we present a new idea for improving Genetic Programming generalization ability. The idea is based on a dynamic two-layered selection algorithm and it is tested on a real-life drug discovery regression application. The algorithm begins using root mean squared error as fitness and the usual tournament selection. A list of individuals called ``repulsors'' is also kept in memory and initialized as empty. As an individual is found to overfit the training set, it is inserted into the list of repulsors. When the list of repulsors is not empty, selection becomes a two-layer algorithm: individuals participating to the tournament are not randomly chosen from the population but are themselves selected, using the average dissimilarity to the repulsors as a criterion to be maximized. Two kinds of similarity/dissimilarity measures are tested for this aim: the well known structural (or edit) distance and the recently defined subtree crossover based similarity measure. Although simple, this idea seems to improve Genetic Programming generalization ability and the presented experimental results show that Genetic Programming generalizes better when subtree crossover based similarity measure is used, at least for the test problems studied in this paper.",
-
notes = "GECCO-2009 A joint meeting of the eighteenth
international conference on genetic algorithms
(ICGA-2009) and the fourteenth annual genetic
programming conference (GP-2009).
ACM Order Number 910092.",
