Publication - Optimising the Topology-Preservation Characteristics of a Discriminator-Based Logic Neural Network
RESEARCH

Optimising the Topology-Preservation Characteristics of a Discriminator-Based Logic Neural Network

Research Area:  
Other topics in Computer Science
    
Type:  
Journal article

 

Year: 1994
Authors: George Tambouratzis
Journal: Pattern Recognition Letters
Volume: 15
Pages: 1019-1028
DOI: 10.1016/0167-8655(94)90034-5
Abstract:
In this article, a self-organising logic neural network is studied. This network successfully clusters input patterns into classes characterised by a high similarity, while assigning these classes to the network nodes so that relationships existing in the pattern space are replicated on the network structure. The network performance is optimised by (i) introducing a mechanism which ensures the efficient use of the network nodes for storage of pattern classes and by (ii) determining the training strategy which results in optimal topology-preservation characteristics.
[Bibtex]