Direct Evolution of Hierarchical Solutions with
Self-Emergent Substructures
X. Li, C. Zhou, W. Xiao, and P. Nelson. The Fourth International Conference on Machine
Learning and Applications (ICMLA'05), page 337--342. Los Angeles, California, IEEE press, (December 2005)
Abstract
Linear genotype representation and modularity have
continuously received extensive attention from the
Genetic Programming (GP) community. The advantages of a
linear genotype include a convenient and efficient
implementation scheme. However, most existing
techniques using a linear genotype follow the
imperative programming language paradigm and a direct
hierarchical composition for the functionality of the
solution is under achieved. Our work is based on Prefix
Gene Expression Programming (P-GEP), a new GP method
featured by a prefix notation based linear genotype
representation. Since P-GEP uses a functional language
paradigm, its framework results in natural self
emergence of substructures as functional components
during the evolution. We propose to preserve and use
potentially useful emergent substructures via a dynamic
substructure library, empowering the algorithm to focus
the search on a higher level of the solution structure.
Preliminary experiments on the benchmark regression
problems have shown the effectiveness of this
approach.
%0 Conference Paper
%1 Substructures(ICMLA05)_XLi
%A Li, Xin
%A Zhou, Chi
%A Xiao, Weimin
%A Nelson, Peter C.
%B The Fourth International Conference on Machine
Learning and Applications (ICMLA'05)
%C Los Angeles, California
%D 2005
%I IEEE press
%K Expression Gene Prefix Programming algorithms, genetic programming,
%P 337--342
%T Direct Evolution of Hierarchical Solutions with
Self-Emergent Substructures
%U http://www.cs.uic.edu/~xli1/papers/Substructures(ICMLA05)_XLi.pdf
%X Linear genotype representation and modularity have
continuously received extensive attention from the
Genetic Programming (GP) community. The advantages of a
linear genotype include a convenient and efficient
implementation scheme. However, most existing
techniques using a linear genotype follow the
imperative programming language paradigm and a direct
hierarchical composition for the functionality of the
solution is under achieved. Our work is based on Prefix
Gene Expression Programming (P-GEP), a new GP method
featured by a prefix notation based linear genotype
representation. Since P-GEP uses a functional language
paradigm, its framework results in natural self
emergence of substructures as functional components
during the evolution. We propose to preserve and use
potentially useful emergent substructures via a dynamic
substructure library, empowering the algorithm to focus
the search on a higher level of the solution structure.
Preliminary experiments on the benchmark regression
problems have shown the effectiveness of this
approach.
@inproceedings{Substructures(ICMLA05)_XLi,
abstract = {Linear genotype representation and modularity have
continuously received extensive attention from the
Genetic Programming (GP) community. The advantages of a
linear genotype include a convenient and efficient
implementation scheme. However, most existing
techniques using a linear genotype follow the
imperative programming language paradigm and a direct
hierarchical composition for the functionality of the
solution is under achieved. Our work is based on Prefix
Gene Expression Programming (P-GEP), a new GP method
featured by a prefix notation based linear genotype
representation. Since P-GEP uses a functional language
paradigm, its framework results in natural self
emergence of substructures as functional components
during the evolution. We propose to preserve and use
potentially useful emergent substructures via a dynamic
substructure library, empowering the algorithm to focus
the search on a higher level of the solution structure.
Preliminary experiments on the benchmark regression
problems have shown the effectiveness of this
approach.},
added-at = {2008-06-19T17:35:00.000+0200},
address = {Los Angeles, California},
author = {Li, Xin and Zhou, Chi and Xiao, Weimin and Nelson, Peter C.},
biburl = {https://www.bibsonomy.org/bibtex/2d745e990f7a24121e8beade625fee355/brazovayeye},
booktitle = {The Fourth International Conference on Machine
Learning and Applications (ICMLA'05)},
interhash = {575763503c49e568c4a1f51881c3d164},
intrahash = {d745e990f7a24121e8beade625fee355},
keywords = {Expression Gene Prefix Programming algorithms, genetic programming,},
month = {December 15-17},
notes = {http://www.cs.csubak.edu/~icmla/icmla05/CFP_Program.html},
pages = {337--342},
publisher = {IEEE press},
timestamp = {2008-06-19T17:45:33.000+0200},
title = {Direct Evolution of Hierarchical Solutions with
Self-Emergent Substructures},
url = {http://www.cs.uic.edu/~xli1/papers/Substructures(ICMLA05)_XLi.pdf},
year = 2005
}