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...
Saved in:
Published in | Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94) Vol. 7; pp. 4349 - 4352 vol.7 |
---|---|
Main Authors | , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
1994
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
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 |