Extracting Rules from Composite Neural Networks for Medical Diagnostic Problems

淡江大學機構典藏 > 工學院 > 電機工程學系暨研究所 > 期刊論文 > Item 987654321/46122

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/46122

题名:	Extracting Rules from Composite Neural Networks for Medical Diagnostic Problems
作者:	蘇木春;Su, Mu-chun;Chang, Hsiao-te
贡献者:	淡江大學電機工程學系
关键词:	expert system;genetic algorithms;medical diagnosis;neural networks;rule extraction
日期:	1998-12-01
上传时间:	2010-03-26 20:59:55 (UTC+8)
出版者:	New York: Springer New York LLC
摘要:	Recently, neural networks have been applied to many medical diagnostic problems because of their appealing properties, robustness, capability of generalization and fault tolerance. Although the predictive accuracy of neural networks may be higher than that of traditional methods (e.g., statistical methods) or human experts, the lack of explanation from a trained neural network leads to the difficulty that users would hesitate to take the advise of a black box on faith alone. This paper presents a class of composite neural networks which are trained in such a way that the values of the network parameters can be utilized to generate If-Then rules on the basis of preselected meaningful coordinates. The concepts and methods presented in the paper are illustrated through one practical example from medical diagnosis.
關聯:	Neural Processing Letters 8(3), pp.253-263
DOI:	10.1023/A:1009681803460
显示于类别:	[電機工程學系暨研究所] 期刊論文

文件中的档案:

档案	大小	格式	浏览次数
index.html	0Kb	HTML	365	检视/开启

在機構典藏中所有的数据项都受到原著作权保护.

TAIR相关文章