Extracting Rules from Composite Neural Networks for Medical Diagnostic Problems
學年 87
學期 1
出版(發表)日期 1998-12-01
作品名稱 Extracting Rules from Composite Neural Networks for Medical Diagnostic Problems
作品名稱(其他語言)
著者 蘇木春; Su, Mu-chun; Chang, Hsiao-te
單位 淡江大學電機工程學系
出版者 New York: Springer New York LLC
著錄名稱、卷期、頁數 Neural Processing Letters 8(3), pp.253-263
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.
關鍵字 expert system; genetic algorithms; medical diagnosis; neural networks; rule extraction
語言 en
ISSN 1370-4621 1573-773X
期刊性質 國外
收錄於
產學合作
通訊作者
審稿制度
國別 USA
公開徵稿
出版型式 電子版
相關連結

機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/46122 )

機構典藏連結