Publication Details
Neural Network for Text Associations
Neural Network, BAM, RCE Classifier
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.
The paper deals with a neural network based on the principle of the Restricted Coulomb Energy classifier, that works as a heteroassociative memory. The short principles of the proposed neural network - topology, learning and retrieving - are described here.
@INPROCEEDINGS{FITPUB6611,
author = "Franti\v{s}ek Zbo\v{r}il",
title = "Neural Network for Text Associations",
pages = "145--150",
booktitle = "Proceedings of XXIInd International Colloquium ASIS 2000",
year = 2000,
location = "Ostrava, CZ",
ISBN = "80-85988-51-8",
language = "english",
url = "https://www.fit.vut.cz/research/publication/6611"
}