Publication detail
The use of the RCE Neural Network in a Pattern Recognition
ZBOŘIL, F. ZBOŘIL, F.
English title
The use of the RCE Neural Network in a Pattern Recognition
Type
conference paper
Language
en
Original abstract
A Restricted Coulomb Energy (RCE) neural network is a specific design of the hypespherical classifier proposed by Reilly in 1982 and it is suitable for classification of nonlinearly separable clusters of patterns in multidimensional pattern spaces. The paper deals with the use of the RCE neural network for the recognition of persons. Two sets of input patterns were used in described experiments. The first set contained pictures of person faces and the second set contained person fingerprints. The short principle and topology of the RCE neural network, learning and retrieving algorithms and mentioned experiments are described in the paper.
English abstract
A Restricted Coulomb Energy (RCE) neural network is a specific design of the hypespherical classifier proposed by Reilly in 1982 and it is suitable for classification of nonlinearly separable clusters of patterns in multidimensional pattern spaces. The paper deals with the use of the RCE neural network for the recognition of persons. Two sets of input patterns were used in described experiments. The first set contained pictures of person faces and the second set contained person fingerprints. The short principle and topology of the RCE neural network, learning and retrieving algorithms and mentioned experiments are described in the paper.
Keywords in English
Neural Networks, RCE Classifier, Pattern Recognition
RIV year
2001
Released
01.01.2000
Location
Ostrava
ISBN
80-85988-44-5
Book
34th Spring International Conference Modelling and Simulation of Systems MOSIS 2000
Pages from–to
65–70
Pages count
6
BIBTEX
@inproceedings{BUT5419,
author="František {Zbořil} and František {Zbořil},
title="The use of the RCE Neural Network in a Pattern Recognition",
booktitle="34th Spring International Conference Modelling and Simulation of Systems MOSIS 2000",
year="2000",
month="January",
pages="65--70",
address="Ostrava",
isbn="80-85988-44-5"
}