Detail publikace
Neural Network for Text Associations
ZBOŘIL, F.
Anglický název
Neural Network for Text Associations
Typ
článek ve sborníku ve WoS nebo Scopus
Jazyk
en
Originální abstrakt
The paper proposes a new neural network based on the principle of the Restricted Coulomb Energy (RCE) classifier. The network has three layers of neurons and it works as a heteroassociative memory. The short principles of the proposed neural network – topology, learning and retrieving – are described in the paper. Experiments with text lines associations that have been done with this neural network and with the Bidirectional Associative Memory (BAM) and a comparison of these results are described in the paper, too.
Anglický abstrakt
The paper proposes a new neural network based on the principle of the Restricted Coulomb Energy (RCE) classifier. The network has three layers of neurons and it works as a heteroassociative memory. The short principles of the proposed neural network – topology, learning and retrieving – are described in the paper. Experiments with text lines associations that have been done with this neural network and with the Bidirectional Associative Memory (BAM) and a comparison of these results are described in the paper, too.
Klíčová slova anglicky
Neural Network, BAM, RCE Classifier
Rok RIV
2001
Vydáno
01.01.2000
Místo
Ostrava
ISBN
80-85988-51-8
Kniha
Proceedings of XXIInd International Colloquium ASIS 2000
Strany od–do
145–150
Počet stran
6
BIBTEX
@inproceedings{BUT5418,
author="František {Zbořil},
title="Neural Network for Text Associations",
booktitle="Proceedings of XXIInd International Colloquium ASIS 2000",
year="2000",
month="January",
pages="145--150",
address="Ostrava",
isbn="80-85988-51-8"
}