This paper presents a method using a genetic algorithm (GA) with a
partial fitness (PF) and a deterministic mutation (DM) to design
a neural pattern recognition system for a rotated coin recognition
problem. In the method, chromosomes in the GA are divided into several
parts. Their PFs are evaluated for GA operations. Furthermore, this
paper introduces the DM based on a neural network learning. A coin
recognition system in this paper includes as a preprocessor the Fourier
transform, which produces rotation invariant features. Those features
are recognized by a multilayered neural network. The GA is utilized
to reduce the number of input signals, Fourier spectra, into the
neural network. It is shown that the present method is better than
conventional GAs on convergence in learning and makes a small-sized
neural network
%0 Conference Paper
%1 Fukumi1996
%A Fukumi, Minoru
%A Akamatsu, Norio
%B Systems, Man, and Cybernetics, 1996. IEEE International Conference
on
%D 1996
%I IEEE Computer Society
%K (artificial Fourier algorithm, algorithms, coin convergence, deterministic features fitness, genetic intelligence), invariant learning learning, multilayer multilayered mutation, network network, neural partial pattern perceptrons, problem, recognition recognitionFourier rotated rotation spectra, system, transform, transforms,
%P 1989--1993
%R 10.1109/ICSMC.1996.565432
%T A method to design a neural pattern recognition system by using a
genetic algorithm with partial fitness and a deterministic mutation
%U http://ieeexplore.ieee.org/iel3/4232/12283/00565432.pdf?tp=&arnumber=565432&isnumber=12283
%V 3
%X This paper presents a method using a genetic algorithm (GA) with a
partial fitness (PF) and a deterministic mutation (DM) to design
a neural pattern recognition system for a rotated coin recognition
problem. In the method, chromosomes in the GA are divided into several
parts. Their PFs are evaluated for GA operations. Furthermore, this
paper introduces the DM based on a neural network learning. A coin
recognition system in this paper includes as a preprocessor the Fourier
transform, which produces rotation invariant features. Those features
are recognized by a multilayered neural network. The GA is utilized
to reduce the number of input signals, Fourier spectra, into the
neural network. It is shown that the present method is better than
conventional GAs on convergence in learning and makes a small-sized
neural network
@inproceedings{Fukumi1996,
abstract = {This paper presents a method using a genetic algorithm (GA) with a
partial fitness (PF) and a deterministic mutation (DM) to design
a neural pattern recognition system for a rotated coin recognition
problem. In the method, chromosomes in the GA are divided into several
parts. Their PFs are evaluated for GA operations. Furthermore, this
paper introduces the DM based on a neural network learning. A coin
recognition system in this paper includes as a preprocessor the Fourier
transform, which produces rotation invariant features. Those features
are recognized by a multilayered neural network. The GA is utilized
to reduce the number of input signals, Fourier spectra, into the
neural network. It is shown that the present method is better than
conventional GAs on convergence in learning and makes a small-sized
neural 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 Akamatsu, Norio},
biburl = {https://www.bibsonomy.org/bibtex/278a755863d7e81fdec33836c03f6036c/cocus},
booktitle = {Systems, Man, and Cybernetics, 1996. IEEE International Conference
on},
booktitleaddon = {October 14--17, 1996},
doi = {10.1109/ICSMC.1996.565432},
file = {:./fukumi1996_00565432-1.pdf:PDF},
interhash = {ec7f0941600f56187934031305e155c0},
intrahash = {78a755863d7e81fdec33836c03f6036c},
keywords = {(artificial Fourier algorithm, algorithms, coin convergence, deterministic features fitness, genetic intelligence), invariant learning learning, multilayer multilayered mutation, network network, neural partial pattern perceptrons, problem, recognition recognitionFourier rotated rotation spectra, system, transform, transforms,},
location = {#ieeeaddr#},
owner = {CK},
pages = {1989--1993},
publisher = {{IEEE} Computer Society},
timestamp = {2011-03-27T19:35:39.000+0200},
title = {A method to design a neural pattern recognition system by using a
genetic algorithm with partial fitness and a deterministic mutation},
titleaddon = {Octpber 14--17, 1996},
url = {http://ieeexplore.ieee.org/iel3/4232/12283/00565432.pdf?tp=&arnumber=565432&isnumber=12283},
urldate = {25-1-2008},
venue = {Beijing, China},
volume = 3,
volumes = {4},
xcrossref = {CK:conf/ieeesmc/1996},
year = 1996
}