Evolution of the Topology and the Weights of Neural Networks using Genetic Programming with a Dual Representation
Created by W.Langdon from
gp-bibliography.bib Revision:1.8010
- @Article{Pujol:1998:etwNNGP,
-
author = "Joao Carlos Figueira Pujol and Riccardo Poli",
-
title = "Evolution of the Topology and the Weights of Neural
Networks using Genetic Programming with a Dual
Representation",
-
journal = "Applied Intelligence",
-
year = "1998",
-
volume = "8",
-
pages = "73--84",
-
email = "J.Pujol@cs.bham.ac.uk R.Poli@cs.bham.ac.uk",
-
keywords = "genetic algorithms, genetic programming, Evolutionary
computation, neural networks, PDGP",
-
broken = "http://www.urano.cdtn.br/~pujol/ai98.ps",
-
URL = "http://cswww.essex.ac.uk/staff/poli/papers/Pujol-AI-1998.pdf",
-
URL = "http://citeseer.ist.psu.edu/336222.html",
-
URL = "http://citeseer.ist.psu.edu/322291.html",
-
DOI = "doi:10.1023/A:1008272615525",
-
size = "12 pages",
-
abstract = "Evolutionary computation is a class of global search
techniques based on the learning process of a
population of potential solutions to a given problem,
that has been successfully applied to a variety of
problems. In this paper a new approach to the
construction of neural networks based on evolutionary
computation is presented. A linear chromosome combined
to a graph representation of the network are used by
genetic operators, which allow the evolution of the
architecture and the weights simultaneously without the
need of local weight optimization. This paper describes
the approach, the operators and reports results of the
application of this technique to several binary
classification problems.",
-
notes = "see also \cite{Pujol:1997:etwNNGP} XOR, 3,4,5 odd
parity, T an C character (TC) recognition problem",
- }
Genetic Programming entries for
Joao Carlos Figueira Pujol
Riccardo Poli
Citations