會議論文
| 學年 | 83 |
|---|---|
| 學期 | 1 |
| 發表日期 | 1994-12-12 |
| 作品名稱 | Neural Network-Based Fuzzy Systems |
| 作品名稱（其他語言） | |
| 著者 | Su, Mu-Chun; Kao, Chien-Jen; Liu, Kai-Ming |
| 作品所屬單位 | 淡江大學電機工程學系 |
| 出版者 | |
| 會議名稱 | 1994 International Computer Symposium Conference |
| 會議地點 | 新北市, 臺灣 |
| 摘要 | In this paper, we discuss how to use FDHECNN's (fuzzy degraded hyperellipsoidal composite neural networks) to extract fuzzy rules for function approximation. The FDHECNN can perform function approximation in the same manner as networks based on Gaussion potential functions, by linear combination of local functions. Furthermore, the output functions of the hidden nodes in the FDHECNN's offer more flexibility than Gaussion potential functions do. A special scheme is developed to find a set of good initial weights in order to speed up the convergence problem. Results of simulations of a system identification demonstrates that the feasibility and robustness of the proposed fuzzy neural networks. |
| 關鍵字 | 模糊類神經網路;模糊規則抽取;函數近似;FDHECNNFuzzy Neural Network;Fuzzy Rule Extraction;Function Approximation;Fdhecnn |
| 語言 | en |
| 收錄於 | |
| 會議性質 | 國際 |
| 校內研討會地點 | |
| 研討會時間 | 19941212~19941215 |
| 通訊作者 | |
| 國別 | TWN |
| 公開徵稿 | Y |
| 出版型式 | 紙本 |
| 出處 | 1994 International Computer Symposium Conference Proceeding Volume 2 of 2，頁1246-1250 |
| 相關連結 |
機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/95869 ) |