Publication - A Logical Neural Network that Adapts to Changes in the Pattern Environment
RESEARCH

A Logical Neural Network that Adapts to Changes in the Pattern Environment

Research Area:  
Other topics in Computer Science
    
Type:  
In Proceedings

 

Year: 1992
Authors: George Tambouratzis; T.J. Stonham
Book title: Proceedings of the 11th IAPR Conference on Pattern Recognition
Pages: 46-49
Address: The Hague, The Netherlands
Organization: IAPR
Date: 30 August-3 September
ISBN: 0-8186-2915-0
DOI: 10.1109/ICPR.1992.201719
Abstract:
An online, unsupervised training algorithm is presented, which allows a logical neural network already trained to identify classes of objects to adapt to changes in the environment. This algorithm enables the system to operate continuously, without danger of overgeneralisation and displays useful noise-reduction properties. Results indicating its capabilities and characteristics in this adaptation task are described. The algorithm's self-organisation characteristics are also evaluated
[Bibtex]