Combining Boolean Neural Architectures for Image Recognition
作者:
A. De Carvalho,
M. C Fairhurst,
D. L Bisset,
期刊:
Connection Science
(Taylor Available online 1997)
卷期:
Volume 9,
issue 4
页码: 405-418
ISSN:0954-0091
年代: 1997
DOI:10.1080/095400997116612
出版商: Taylor & Francis Group
关键词: Weightless Neural Networks;Character Recognition;Modular Architectures
数据来源: Taylor
摘要:
This paper presents a completely integrated Boolean neural architecture, where a selforganizing Boolean neural network (SOFT) is used as a front-end processor to a feedforward Boolean network based on goal-seeking principles (GSN f). This paper will evaluate the advantages of the integrated SOFT-GSN f over GSN f by showing its increased effectiveness in an optical character recognition task.
点击下载:
PDF (235KB)
返 回