Neural Network for Text Associations

article in a collection out of WoS and Scopus

English

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.

Neural Network, BAM, RCE Classifier

ZBOŘIL, F.

2001

1. 1. 2000

Marq software s.r.o.

Ostrava

80-85988-51-8

Proceedings of XXIInd International Colloquium ASIS 2000

145

150

6