Publication - Evaluating the Topology-Preservation Capabilities of a Self-Organising Logical Neural Network
RESEARCH

Evaluating the Topology-Preservation Capabilities of a Self-Organising Logical Neural Network

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

 

Year: 1993
Authors: George Tambouratzis; T.J. Stonham
Journal: Pattern Recognition Letters
Volume: 14
Number: 11
Pages: 927-934
DOI: 10.1016/0167-8655(93)90157-9
Abstract:
An unsupervised learning algorithm which enables a logical neural network to separate different classes of binary images while at the same time creating a topology-preserving mapping of the input space is described. Results concerning its successful application to character separation and recognition are presented and the quality of the mappings generated by the system is evaluated.
[Bibtex]