A Multiple-Output Program Tree Structure in Genetic
Programming
Y. Zhang, and M. Zhang. Proceedings of The Second Asian-Pacific Workshop on
Genetic Programming, page 12pp. Cairns, Australia, (6-7 December 2004)
Abstract
program tree structure in genetic programming which
outputs multiple related values, hence serves as a more
coherent multiclass classifier. The multiple outputting
effect of the tree is achieved by making it simulate a
kind of directed acyclic graph. The approach is
examined and compared with the basic genetic
programming approach on four multiclass object
classification tasks with varying difficulty. The
results show that the new approach greatly outperforms
the basic genetic programming approach on all the
tasks.
%0 Conference Paper
%1 Zhang:2004:aspgp
%A Zhang, Yun
%A Zhang, Mengjie
%B Proceedings of The Second Asian-Pacific Workshop on
Genetic Programming
%C Cairns, Australia
%D 2004
%E Mckay, R I
%E Cho, Sung-Bae
%K algorithms, genetic programming
%P 12pp
%T A Multiple-Output Program Tree Structure in Genetic
Programming
%U http://www.mcs.vuw.ac.nz/~mengjie/papers/yun-meng-apwgp04.pdf
%X program tree structure in genetic programming which
outputs multiple related values, hence serves as a more
coherent multiclass classifier. The multiple outputting
effect of the tree is achieved by making it simulate a
kind of directed acyclic graph. The approach is
examined and compared with the basic genetic
programming approach on four multiclass object
classification tasks with varying difficulty. The
results show that the new approach greatly outperforms
the basic genetic programming approach on all the
tasks.
@inproceedings{Zhang:2004:aspgp,
abstract = {program tree structure in genetic programming which
outputs multiple related values, hence serves as a more
coherent multiclass classifier. The multiple outputting
effect of the tree is achieved by making it simulate a
kind of directed acyclic graph. The approach is
examined and compared with the basic genetic
programming approach on four multiclass object
classification tasks with varying difficulty. The
results show that the new approach greatly outperforms
the basic genetic programming approach on all the
tasks.},
added-at = {2008-06-19T17:46:40.000+0200},
address = {Cairns, Australia},
author = {Zhang, Yun and Zhang, Mengjie},
biburl = {https://www.bibsonomy.org/bibtex/21f455e2a30775f8a477aeddfe596acb8/brazovayeye},
booktitle = {Proceedings of The Second Asian-Pacific Workshop on
Genetic Programming},
editor = {Mckay, R I and Cho, Sung-Bae},
interhash = {406a7b02d0e73972f90a8dd0d1b36103},
intrahash = {1f455e2a30775f8a477aeddfe596acb8},
keywords = {algorithms, genetic programming},
month = {6-7 December},
notes = {http://www.itee.adfa.edu.au/~rim/ASPGP/programme.html},
pages = {12pp},
size = {13 pages},
timestamp = {2008-06-19T17:55:49.000+0200},
title = {A Multiple-Output Program Tree Structure in Genetic
Programming},
url = {http://www.mcs.vuw.ac.nz/~mengjie/papers/yun-meng-apwgp04.pdf},
year = 2004
}