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

標題:A novel class of neural networks with quadratic junctions
學年80
學期1
發表日期1991/10/13
作品名稱A novel class of neural networks with quadratic junctions
作品名稱(其他語言)
著者DeClaris, Nicholas; Su, Mu-chun
作品所屬單位淡江大學電機工程學系
出版者IEEE
會議名稱Proceedings of the IEEE international conferences on systems
會議地點Charlottesville, VA
摘要The authors discuss the architecture and training properties of a multilayer feedforward neural network class that uses quadratic junctions in a neural architecture that uses effectively the backpropagation learning algorithm given by P.J. Werbos (1989). Both the architecture of the quadratic junctions and the backpropagation were adopted so as to endow the networks with appealing training properties (under supervision) and acceptable generalizations. Complexity and learning aspects of this class are examined and compared with traditional networks that use linear junctions.
關鍵字
語言英文
收錄於
會議性質國際
校內研討會地點
研討會時間19911013~16
通訊作者
國別美國
公開徵稿Y
出版型式紙本
出處Proceedings of the IEEE international conferences on systems, man, and cybernetics, v.3,p.p1557 - 1562
相關連結
Google+ 推薦功能,讓全世界都能看到您的推薦!