Publication - Self-Organisation in Complex Pattern Spaces Using a Logic Neural Network
RESEARCH

Self-Organisation in Complex Pattern Spaces Using a Logic Neural Network

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

 

Year: 1994
Authors: George Tambouratzis; D. Tambouratzis
Journal: Network: Computation in Neural Systems
Volume: 5
Pages: 599-617
Abstract:
This article investigates the behaviour of a self-organising logic neural network when it is tasksd with clustering complex data spaces. The network is based on the discriminator-node structure and is trained using an unsupervised-learning adaptation rule. The network performance is evaluated by applying it to clustering tasks involving identifiable classes, each of which consists of a lrage number of distinct subclasses. The results presented are supported by a statistical analysis, which indicates that the system is indeed suited to clustering such complex datasets.
[Bibtex]