| 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 | en |
| 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 | USA |
| 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 |
機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/70269 ) |
GoogleAnalytics