Publication detail

Neural Network for Text Associations

ZBOŘIL, F.

Original Title

Neural Network for Text Associations

English Title

Neural Network for Text Associations

Type

conference paper

Language

en

Original Abstract

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.

English abstract

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.

Keywords

Neural Network, BAM, RCE Classifier

RIV year

2001

Released

01.01.2000

Location

Ostrava

ISBN

80-85988-51-8

Book

Proceedings of XXIInd International Colloquium ASIS 2000

Pages from

145

Pages to

150

Pages count

6

BibTex


@inproceedings{BUT5418,
  author="František {Zbořil}",
  title="Neural Network for Text Associations",
  annote="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.",
  booktitle="Proceedings of XXIInd International Colloquium ASIS 2000",
  chapter="5418",
  year="2000",
  month="january",
  pages="145--150",
  type="conference paper"
}