首页   按字顺浏览 期刊浏览 卷期浏览 Combining Boolean Neural Architectures for Image Recognition
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