Title :
A modular Boolean architecture for pattern recognition
Author :
de Carvalho, A. ; Fairhurst, M.C. ; Bisset, D.L.
Author_Institution :
Electron. Eng. Labs., Kent Univ., Canterbury, UK
fDate :
27 Jun-2 Jul 1994
Abstract :
This paper describes a modular neural structure where a self-organising Boolean neural network architecture (SOFT) is used as a front-end processor to a feedforward neural architecture based on goal-seeking principles (GSNf). The characteristics of this architecture are illustrated by considering its application to a character recognition problem
Keywords :
character recognition; feature extraction; feedforward neural nets; neural net architecture; parallel architectures; self-organising feature maps; character recognition; feedforward neural architecture; goal-seeking principles; modular Boolean architecture; pattern recognition; self organising feature extractor; self-organising Boolean neural network; Electronic mail; Feature extraction; Hardware; Laboratories; Neural networks; Neurons; Pattern recognition; Pixel; Random access memory; Visual system;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374967
