Probabilistic Model Building and Competent Genetic
Programming
K. Sastry, und D. Goldberg. Genetic Programming Theory and Practise, Kapitel 13, Kluwer, (2003)
Zusammenfassung
a probabilistic model building genetic programming
(PMBGP) developed based on the extended compact genetic
algorithm (eCGA). Unlike traditional genetic
programming, which use fixed recombination operators,
the proposed PMBGA adapts linkages. The proposed
algorithms, called the extended compact genetic
programming (eCGP) adaptively identifies and exchanges
non-overlapping building blocks by constructing and
sampling probabilistic models of promising solutions.
The results show that eCGP scales-up polynomially with
the problem size (the number of functionals and
terminals) on both GP-easy problem and boundedly
difficult GP-hard problem.
%0 Book Section
%1 sastry:2003:GPTP13
%A Sastry, Kumara
%A Goldberg, David E.
%B Genetic Programming Theory and Practise
%D 2003
%E Riolo, Rick L.
%E Worzel, Bill
%I Kluwer
%K Competent Extended Linkage Probabilistic adaptation, algorithm algorithms, building, compact genetic learning, model program, programming,
%P 205--220
%T Probabilistic Model Building and Competent Genetic
Programming
%U http://gal31.ge.uiuc.edu/kumara/wp-content/files/2003013.pdf
%X a probabilistic model building genetic programming
(PMBGP) developed based on the extended compact genetic
algorithm (eCGA). Unlike traditional genetic
programming, which use fixed recombination operators,
the proposed PMBGA adapts linkages. The proposed
algorithms, called the extended compact genetic
programming (eCGP) adaptively identifies and exchanges
non-overlapping building blocks by constructing and
sampling probabilistic models of promising solutions.
The results show that eCGP scales-up polynomially with
the problem size (the number of functionals and
terminals) on both GP-easy problem and boundedly
difficult GP-hard problem.
%& 13
%@ 1-4020-7581-2
@incollection{sastry:2003:GPTP13,
abstract = {a probabilistic model building genetic programming
(PMBGP) developed based on the extended compact genetic
algorithm (eCGA). Unlike traditional genetic
programming, which use fixed recombination operators,
the proposed PMBGA adapts linkages. The proposed
algorithms, called the extended compact genetic
programming (eCGP) adaptively identifies and exchanges
non-overlapping building blocks by constructing and
sampling probabilistic models of promising solutions.
The results show that eCGP scales-up polynomially with
the problem size (the number of functionals and
terminals) on both GP-easy problem and boundedly
difficult GP-hard problem.},
added-at = {2008-06-19T17:46:40.000+0200},
author = {Sastry, Kumara and Goldberg, David E.},
biburl = {https://www.bibsonomy.org/bibtex/2af5bfd46af59f94571a168a418e25283/brazovayeye},
booktitle = {Genetic Programming Theory and Practise},
chapter = 13,
editor = {Riolo, Rick L. and Worzel, Bill},
interhash = {39bd8a90d004afcd3cfa9518b1e8a0cb},
intrahash = {af5bfd46af59f94571a168a418e25283},
isbn = {1-4020-7581-2},
keywords = {Competent Extended Linkage Probabilistic adaptation, algorithm algorithms, building, compact genetic learning, model program, programming,},
pages = {205--220},
publisher = {Kluwer},
size = {14 pages},
timestamp = {2008-06-19T17:51:04.000+0200},
title = {Probabilistic Model Building and Competent Genetic
Programming},
url = {http://gal31.ge.uiuc.edu/kumara/wp-content/files/2003013.pdf},
year = 2003
}