AN INTEGRATED BOOLEAN NEURAL-NETWORK FOR PATTERN-CLASSIFICATION

被引:6
|
作者
DECARVALHO, A [1 ]
FAIRHURST, MC [1 ]
BISSET, DL [1 ]
机构
[1] UNIV KENT,ELECTR ENGN LABS,CANTERBURY CT2 7NT,KENT,ENGLAND
关键词
BOOLEAN NEURAL NETWORKS; PATTERN RECOGNITION; INTEGRATED ARCHITECTURES;
D O I
10.1016/0167-8655(94)90009-4
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper describes an integrated approach to pattern classification where a self-organising Boolean neural network architecture is used as a front-end processor to a feedforward neural architecture based on goal-seeking principles (the GSN architecture). The performance of the integrated architecture is illustrated by considering its application to a character recognition problem.
引用
收藏
页码:807 / 813
页数:7
相关论文
共 50 条