A self-organising discriminator-based logic neural network is compared to the similarly-structured supervised WISARD neural network on the basis of their performance in a pattern recognition task. The self-organising system is shown to possess a superior performance in learning environments where the training patterns have a high degree of variability.
References
-
-
1)
-
G. Tambouratzis ,
T.J. Stonham ,
I. Aleksander ,
J. Taylor
.
(1992)
Implementing hard self-organisation tasks using logical neural networks, Artificial neural networks-II.
-
2)
-
I. Aleksander ,
W.V. Thomas ,
P.A. Bowden
.
WISARD: A radical step forward in image recognition.
Sensor Rev.
,
120 -
124
-
3)
-
I. Aleksander ,
H. Morton
.
(1990)
An introduction to neural computing.
-
4)
-
Tambouratzis, G., Stonham, T.J.: `Data clustering in complex pattern spaces using a self-organising logicneural network', Proc. 1993 Weightless Neural Network Workshop, 6–7 April 1993, York, UK, p. 70–75.
-
5)
-
G. Tambouratzis ,
T.J. Stonham
.
Evaluating the topology-preservation capabilities of a self-organisinglogical neural network.
Pattern Recog. Lett.
,
11 ,
927 -
934
-
6)
-
T. Kohonen
.
(1989)
Self-organisation and associative memory.
http://iet.metastore.ingenta.com/content/journals/10.1049/el_19940127
Related content
content/journals/10.1049/el_19940127
pub_keyword,iet_inspecKeyword,pub_concept
6
6