GP for Object Classification: Brood Size in Brood
Recombination Crossover
M. Zhang, X. Gao, and W. Lou. Australian Conference on Artificial Intelligence, volume 4304 of Lecture Notes in Computer Science, page 274--284. Hobart, Australia, Springer, (December 2006)
DOI: doi:10.1007/11941439_31
Abstract
The brood size plays an important role in the brood
recombination crossover method in genetic programming.
However, there has not been any thorough investigation
on the brood size and the methods for setting this size
have not been effectively examined. This paper
investigates a number of new developments of brood size
in the brood recombination crossover method in GP. We
first investigate the effect of different fixed brood
sizes, then construct three dynamic models for setting
the brood size. These developments are examined and
compared with the standard crossover operator on three
object classification problems of increasing
difficulty. The results suggest that the brood
recombination methods with all the new developments
outperforms the standard crossover operator for all the
problems. As the brood size increases, the system
effective performance can be improved. When it exceeds
a certain point, however, the effective performance
will not be improved and the system will become less
efficient. Investigation of three dynamic models for
the brood size reveals that a good variable brood size
which is dynamically set with the number of generations
can further improve the system performance over the
fixed brood sizes.
%0 Conference Paper
%1 DBLP:conf/ausai/ZhangGL06
%A Zhang, Mengjie
%A Gao, Xiaoying
%A Lou, Weijun
%B Australian Conference on Artificial Intelligence
%C Hobart, Australia
%D 2006
%E Sattar, Abdul
%E Kang, Byeong Ho
%I Springer
%K algorithms, genetic programming
%P 274--284
%R doi:10.1007/11941439_31
%T GP for Object Classification: Brood Size in Brood
Recombination Crossover
%V 4304
%X The brood size plays an important role in the brood
recombination crossover method in genetic programming.
However, there has not been any thorough investigation
on the brood size and the methods for setting this size
have not been effectively examined. This paper
investigates a number of new developments of brood size
in the brood recombination crossover method in GP. We
first investigate the effect of different fixed brood
sizes, then construct three dynamic models for setting
the brood size. These developments are examined and
compared with the standard crossover operator on three
object classification problems of increasing
difficulty. The results suggest that the brood
recombination methods with all the new developments
outperforms the standard crossover operator for all the
problems. As the brood size increases, the system
effective performance can be improved. When it exceeds
a certain point, however, the effective performance
will not be improved and the system will become less
efficient. Investigation of three dynamic models for
the brood size reveals that a good variable brood size
which is dynamically set with the number of generations
can further improve the system performance over the
fixed brood sizes.
%@ 3-540-49787-0
@inproceedings{DBLP:conf/ausai/ZhangGL06,
abstract = {The brood size plays an important role in the brood
recombination crossover method in genetic programming.
However, there has not been any thorough investigation
on the brood size and the methods for setting this size
have not been effectively examined. This paper
investigates a number of new developments of brood size
in the brood recombination crossover method in GP. We
first investigate the effect of different fixed brood
sizes, then construct three dynamic models for setting
the brood size. These developments are examined and
compared with the standard crossover operator on three
object classification problems of increasing
difficulty. The results suggest that the brood
recombination methods with all the new developments
outperforms the standard crossover operator for all the
problems. As the brood size increases, the system
effective performance can be improved. When it exceeds
a certain point, however, the effective performance
will not be improved and the system will become less
efficient. Investigation of three dynamic models for
the brood size reveals that a good variable brood size
which is dynamically set with the number of generations
can further improve the system performance over the
fixed brood sizes.},
added-at = {2008-06-19T17:46:40.000+0200},
address = {Hobart, Australia},
author = {Zhang, Mengjie and Gao, Xiaoying and Lou, Weijun},
bibsource = {DBLP, http://dblp.uni-trier.de},
biburl = {https://www.bibsonomy.org/bibtex/2bdbeb4a5102204f3f35edb94db3b4d40/brazovayeye},
booktitle = {Australian Conference on Artificial Intelligence},
doi = {doi:10.1007/11941439_31},
editor = {Sattar, Abdul and Kang, Byeong Ho},
interhash = {e75e95e915cc8b0bd288ade431433361},
intrahash = {bdbeb4a5102204f3f35edb94db3b4d40},
isbn = {3-540-49787-0},
keywords = {algorithms, genetic programming},
month = {December 4-8},
pages = {274--284},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
size = {11 pages},
timestamp = {2008-06-19T17:55:45.000+0200},
title = {{GP} for Object Classification: Brood Size in Brood
Recombination Crossover},
volume = 4304,
year = 2006
}