Designing a neural network by a genetic algorithm with partial fitness
M. Fukumi, S. Omatu, and Y. Nishikawa. Proceedings of the IEEE International joint Conference on Neural
Networks 1995, IJCNN'95, 4, page 1834--1838. IEEE Computer Society, (November 1995)
DOI: 10.1109/ICNN.1995.488900
Abstract
This paper presents a method of using the genetic algorithm (GA) with
partial fitness (PF) to design a neural network for coin recognition.
The method divides a chromosome in the GA into several parts, the
PFs of which are evaluated for GA operations. Each part independently
performs selection and crossover operations in the GA. Such a technique
improves performance in learning of the GA. This paper applies the
method to a rotated coin recognition problem to examine its effectiveness.
The coin recognition system described consists of a preprocessor
with Fourier transform and a multilayered network. The method is
utilized to reduce the number of input signals, Fourier spectra,
of the multilayered network. It is shown that the method is better
than the conventional GA on convergence in learning and makes a smaller
size network
%0 Conference Paper
%1 Fukumi1995
%A Fukumi, Minoru
%A Omatu, Sigeru
%A Nishikawa, Yoshikazu
%B Proceedings of the IEEE International joint Conference on Neural
Networks 1995, IJCNN'95
%D 1995
%I IEEE Computer Society
%K (artificial Fourier algorithm, algorithms, chromosome, coin convergence convergence, crossover feedforward fitness, genetic intelligence), learning learning, methods, nets, network, neural numerical object of operation operation, partial recognition recognitionFourier selection spectra, system, transform transform,
%P 1834--1838
%R 10.1109/ICNN.1995.488900
%T Designing a neural network by a genetic algorithm with partial fitness
%U http://ieeexplore.ieee.org/iel2/3505/10434/00488900.pdf?tp=&arnumber=488900&isnumber=10434
%V 4
%X This paper presents a method of using the genetic algorithm (GA) with
partial fitness (PF) to design a neural network for coin recognition.
The method divides a chromosome in the GA into several parts, the
PFs of which are evaluated for GA operations. Each part independently
performs selection and crossover operations in the GA. Such a technique
improves performance in learning of the GA. This paper applies the
method to a rotated coin recognition problem to examine its effectiveness.
The coin recognition system described consists of a preprocessor
with Fourier transform and a multilayered network. The method is
utilized to reduce the number of input signals, Fourier spectra,
of the multilayered network. It is shown that the method is better
than the conventional GA on convergence in learning and makes a smaller
size network
@inproceedings{Fukumi1995,
abstract = {This paper presents a method of using the genetic algorithm (GA) with
partial fitness (PF) to design a neural network for coin recognition.
The method divides a chromosome in the GA into several parts, the
PFs of which are evaluated for GA operations. Each part independently
performs selection and crossover operations in the GA. Such a technique
improves performance in learning of the GA. This paper applies the
method to a rotated coin recognition problem to examine its effectiveness.
The coin recognition system described consists of a preprocessor
with Fourier transform and a multilayered network. The method is
utilized to reduce the number of input signals, Fourier spectra,
of the multilayered network. It is shown that the method is better
than the conventional GA on convergence in learning and makes a smaller
size network},
added-at = {2011-03-27T19:35:34.000+0200},
affiliation = {University of Tokushima, Faculty of Engineering, Department of Information
Science and Intelligent Systems},
author = {Fukumi, Minoru and Omatu, Sigeru and Nishikawa, Yoshikazu},
biburl = {https://www.bibsonomy.org/bibtex/2b3fb295df741fb9bf9424735d707e983/cocus},
booktitle = {Proceedings of the IEEE International joint Conference on Neural
Networks 1995, IJCNN'95},
booktitleaddon = {Jun 27 -- Jul 2, 1995},
doi = {10.1109/ICNN.1995.488900},
file = {:./fukumi1995_00488900.pdf:PDF},
interhash = {8bc4448889bcc2ee1fa4c697ea8e504a},
intrahash = {b3fb295df741fb9bf9424735d707e983},
keywords = {(artificial Fourier algorithm, algorithms, chromosome, coin convergence convergence, crossover feedforward fitness, genetic intelligence), learning learning, methods, nets, network, neural numerical object of operation operation, partial recognition recognitionFourier selection spectra, system, transform transform,},
location = {#ieeeaddr#},
month = nov,
owner = {CK},
pages = {1834--1838},
publisher = {{IEEE} Computer Society},
timestamp = {2011-03-27T19:35:39.000+0200},
title = {Designing a neural network by a genetic algorithm with partial fitness},
titleaddon = {\noop{}},
url = {http://ieeexplore.ieee.org/iel2/3505/10434/00488900.pdf?tp=&arnumber=488900&isnumber=10434},
urldate = {25-1-2008},
venue = {Beijing, China},
volume = 4,
volumes = {6},
xcrossref = {CK:conf/ijcnn/1995},
year = 1995
}