A modular Boolean architecture for pattern recognition

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 (GSN/sup f/). The characteristics of this architecture are illustrated by consider...

Full description

Saved in:
Bibliographic Details
Published inProceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94) Vol. 7; pp. 4349 - 4352 vol.7
Main Authors de Carvalho, A., Fairhurst, M.C., Bisset, D.L.
Format Conference Proceeding
LanguageEnglish
Published IEEE 1994
Subjects
Electronic mail
Feature extraction
Hardware
Laboratories
Neural networks
Neurons
Pattern recognition
Pixel
Random access memory
Visual system
Online AccessGet full text

Cover

More Information
Summary: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 (GSN/sup f/). The characteristics of this architecture are illustrated by considering its application to a character recognition problem.< >
ISBN:078031901X
9780780319011
DOI:10.1109/ICNN.1994.374967