教師資料查詢 | 類別: 期刊論文 | 教師: 蘇木春 SU MU-CHUN (瀏覽個人網頁)

標題: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
語言英文
ISSN1370-4621;1573-773X
期刊性質國外
收錄於
產學合作
通訊作者
審稿制度
國別美國
公開徵稿
出版型式電子版
相關連結
Google+ 推薦功能,讓全世界都能看到您的推薦!