Detail publikačního výsledku

Neural Network for Text Associations

ZBOŘIL, F.

Originální název

Neural Network for Text Associations

Anglický název

Neural Network for Text Associations

Druh

Stať ve sborníku mimo WoS a Scopus

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

Neural Network, BAM, RCE Classifier

Klíčová slova v angličtině

Neural Network, BAM, RCE Classifier

Autoři

ZBOŘIL, F.

Vydáno

01.01.2000

Nakladatel

Marq software s.r.o.

Místo

Ostrava

ISBN

80-85988-51-8

Kniha

Proceedings of XXIInd International Colloquium ASIS 2000

Strany od

145

Strany do

150

Strany počet

6

BibTex

@inproceedings{BUT5418,
  author="František {Zbořil}",
  title="Neural Network for Text Associations",
  booktitle="Proceedings of XXIInd International Colloquium ASIS 2000",
  year="2000",
  pages="145--150",
  publisher="Marq software s.r.o.",
  address="Ostrava",
  isbn="80-85988-51-8"
}