Condition Matrix Based Genetic Programming for Rule
Learning
J. Wang, K. Lee, and K. Leung. 18th IEEE International Conference on Tools with
Artificial Intelligence (ICTAI'06), page 315--322. Arlington, VA, USA, IEEE Computer Society, (November 2006)
DOI: doi:10.1109/ICTAI.2006.45
Abstract
Most genetic programming paradigms are
population-based and require huge amount of memory. In
this paper, we review the Instruction Matrix based
Genetic Programming which maintains all program
components in a instruction matrix (IM) instead of
manipulating a population of programs. A genetic
program is extracted from the matrix just before it is
being evaluated. After each evaluation, the fitness of
the genetic program is propagated to its corresponding
cells in the matrix. Then, we extend the instruction
matrix to the condition matrix (CM) for generating rule
base from datasets. CM keeps some of characteristics of
IM and incorporates the information about rule
learning. In the evolving process, we adopt an elitist
idea to keep the better rules alive to the end. We
consider that genetic selection maybe lead to the huge
size of rule set, so the reduct theory borrowed from
Rough Sets is used to cut the volume of rules and keep
the same fitness as the original rule set. In
experiments, we compare the performance of Condition
Matrix for Rule Learning (CMRL) with other traditional
algorithms. Results are presented in detail and the
competitive advantage and drawbacks of CMRL are
discussed.
%0 Conference Paper
%1 conf/ictai/WangLL06
%A Wang, Jin Feng
%A Lee, Kin-Hong
%A Leung, Kwong-Sak
%B 18th IEEE International Conference on Tools with
Artificial Intelligence (ICTAI'06)
%C Arlington, VA, USA
%D 2006
%I IEEE Computer Society
%K algorithms, genetic programming
%P 315--322
%R doi:10.1109/ICTAI.2006.45
%T Condition Matrix Based Genetic Programming for Rule
Learning
%U http://doi.ieeecomputersociety.org/10.1109/ICTAI.2006.45
%X Most genetic programming paradigms are
population-based and require huge amount of memory. In
this paper, we review the Instruction Matrix based
Genetic Programming which maintains all program
components in a instruction matrix (IM) instead of
manipulating a population of programs. A genetic
program is extracted from the matrix just before it is
being evaluated. After each evaluation, the fitness of
the genetic program is propagated to its corresponding
cells in the matrix. Then, we extend the instruction
matrix to the condition matrix (CM) for generating rule
base from datasets. CM keeps some of characteristics of
IM and incorporates the information about rule
learning. In the evolving process, we adopt an elitist
idea to keep the better rules alive to the end. We
consider that genetic selection maybe lead to the huge
size of rule set, so the reduct theory borrowed from
Rough Sets is used to cut the volume of rules and keep
the same fitness as the original rule set. In
experiments, we compare the performance of Condition
Matrix for Rule Learning (CMRL) with other traditional
algorithms. Results are presented in detail and the
competitive advantage and drawbacks of CMRL are
discussed.
%@ 0-7695-2728-0
@inproceedings{conf/ictai/WangLL06,
abstract = {Most genetic programming paradigms are
population-based and require huge amount of memory. In
this paper, we review the Instruction Matrix based
Genetic Programming which maintains all program
components in a instruction matrix (IM) instead of
manipulating a population of programs. A genetic
program is extracted from the matrix just before it is
being evaluated. After each evaluation, the fitness of
the genetic program is propagated to its corresponding
cells in the matrix. Then, we extend the instruction
matrix to the condition matrix (CM) for generating rule
base from datasets. CM keeps some of characteristics of
IM and incorporates the information about rule
learning. In the evolving process, we adopt an elitist
idea to keep the better rules alive to the end. We
consider that genetic selection maybe lead to the huge
size of rule set, so the reduct theory borrowed from
Rough Sets is used to cut the volume of rules and keep
the same fitness as the original rule set. In
experiments, we compare the performance of Condition
Matrix for Rule Learning (CMRL) with other traditional
algorithms. Results are presented in detail and the
competitive advantage and drawbacks of CMRL are
discussed.},
added-at = {2008-06-19T17:35:00.000+0200},
address = {Arlington, VA, USA},
author = {Wang, Jin Feng and Lee, Kin-Hong and Leung, Kwong-Sak},
bibdate = {2007-01-04},
bibsource = {DBLP,
http://dblp.uni-trier.de/db/conf/ictai/ictai2006.html#WangLL06},
biburl = {https://www.bibsonomy.org/bibtex/205a2fda2b8340f386d7a18e8a466a245/brazovayeye},
booktitle = {18th IEEE International Conference on Tools with
Artificial Intelligence (ICTAI'06)},
doi = {doi:10.1109/ICTAI.2006.45},
interhash = {ed213547f434a8f10248327af2ec3e58},
intrahash = {05a2fda2b8340f386d7a18e8a466a245},
isbn = {0-7695-2728-0},
keywords = {algorithms, genetic programming},
month = {November 13-15},
notes = {http://www.nvc.cs.vt.edu/ictai06/},
pages = {315--322},
publisher = {IEEE Computer Society},
timestamp = {2008-06-19T17:53:51.000+0200},
title = {Condition Matrix Based Genetic Programming for Rule
Learning},
url = {http://doi.ieeecomputersociety.org/10.1109/ICTAI.2006.45},
year = 2006
}