an evolutionary algorithm-based approach to model
selection and demonstrates its effectiveness in using
the information content of ecological data to choose
the correct model structure. Experiments with a
modified genetic algorithm are described that combine
parsimony with a novel gene regulation mechanism. This
combination creates evolvable switches that implement
functional variable-length genomes in the GA that allow
for simultaneous model selection and parameter fitting.
In effect, the GA orchestrates a competition among a
community of models. Parsimony is implemented via the
Akaike Information Criterion, and gene regulation uses
a modulo function to overload the gene values and
create an evolvable binary switch. The approach is
shown to successfully specify the correct model
structure in experiments with a nested set of
polynomial test models and complex biological
simulation models, even when Gaussian noise is added to
the data.
Special Issue on Biological Applications of Genetic
and Evolutionary Computation Guest Editor(s): Wolfgang
Banzhaf , James Foster
(1) Botany, University of Vermont, Burlington, VT,
05405-0086
(2) Mathematics & Statistics, University of Vermont,
Burlington, VT, 05401-0086-3357
%0 Journal Article
%1 hoffmann:2004:GPEM
%A Hoffmann, James P.
%A Ellingwood, Christopher D.
%A Bonsu, Osei M.
%A Bentil, Daniel E.
%D 2004
%J Genetic Programming and Evolvable Machines
%K algorithms, complexity-based fitness, genetic model parsimony, programming, representation selection, variable-length
%N 2
%P 229--241
%R doi:10.1023/B:GENP.0000023690.71330.42
%T Ecological Model Selection via Evolutionary
Computation and Information Theory
%V 5
%X an evolutionary algorithm-based approach to model
selection and demonstrates its effectiveness in using
the information content of ecological data to choose
the correct model structure. Experiments with a
modified genetic algorithm are described that combine
parsimony with a novel gene regulation mechanism. This
combination creates evolvable switches that implement
functional variable-length genomes in the GA that allow
for simultaneous model selection and parameter fitting.
In effect, the GA orchestrates a competition among a
community of models. Parsimony is implemented via the
Akaike Information Criterion, and gene regulation uses
a modulo function to overload the gene values and
create an evolvable binary switch. The approach is
shown to successfully specify the correct model
structure in experiments with a nested set of
polynomial test models and complex biological
simulation models, even when Gaussian noise is added to
the data.
@article{hoffmann:2004:GPEM,
abstract = {an evolutionary algorithm-based approach to model
selection and demonstrates its effectiveness in using
the information content of ecological data to choose
the correct model structure. Experiments with a
modified genetic algorithm are described that combine
parsimony with a novel gene regulation mechanism. This
combination creates evolvable switches that implement
functional variable-length genomes in the GA that allow
for simultaneous model selection and parameter fitting.
In effect, the GA orchestrates a competition among a
community of models. Parsimony is implemented via the
Akaike Information Criterion, and gene regulation uses
a modulo function to overload the gene values and
create an evolvable binary switch. The approach is
shown to successfully specify the correct model
structure in experiments with a nested set of
polynomial test models and complex biological
simulation models, even when Gaussian noise is added to
the data.},
added-at = {2008-06-19T17:35:00.000+0200},
author = {Hoffmann, James P. and Ellingwood, Christopher D. and Bonsu, Osei M. and Bentil, Daniel E.},
biburl = {https://www.bibsonomy.org/bibtex/2b0234ff027a0b0b633bada8f3dbcf856/brazovayeye},
doi = {doi:10.1023/B:GENP.0000023690.71330.42},
interhash = {46a7337ba0fa800f206187572d522ed7},
intrahash = {b0234ff027a0b0b633bada8f3dbcf856},
issn = {1389-2576},
journal = {Genetic Programming and Evolvable Machines},
keywords = {algorithms, complexity-based fitness, genetic model parsimony, programming, representation selection, variable-length},
month = {June},
notes = {Special Issue on Biological Applications of Genetic
and Evolutionary Computation Guest Editor(s): Wolfgang
Banzhaf , James Foster
(1) Botany, University of Vermont, Burlington, VT,
05405-0086
(2) Mathematics & Statistics, University of Vermont,
Burlington, VT, 05401-0086-3357},
number = 2,
pages = {229--241},
timestamp = {2008-06-19T17:41:37.000+0200},
title = {Ecological Model Selection via Evolutionary
Computation and Information Theory},
volume = 5,
year = 2004
}