查詢結果分析
來源資料
相關文獻
- A Neural Net Architecture for Various Learning Processes on AC Skin Analysis
- Training Time of Grid Gaussian Networks Increases at Power Order of Input Dimension
- An On-Line Learning Neural Network for Radar Signal Classification
- 類神經網路與模糊理論的系統設計理念
- 利用類神經網路建模估測風力發電系統發電量
- 遞迴式類神經模式於日流量預測之應用
- Neural Network Procedures for Taguchi's Dynamic Problems
- A Fast and Efficient Competitive Learning Design Algorithm Based on Weight Vector Training in Transform Domain
- 專家系統振動訊號圖型判別之研究
- 反傳遞模糊類神經網路於流量推估之應用
頁籤選單縮合
題 名 | A Neural Net Architecture for Various Learning Processes on AC Skin Analysis=運用類神經網路架構之各類學習法則於交流膚參數 |
---|---|
作 者 | 張保榮; | 書刊名 | 高苑學報 |
卷 期 | 5:2 1996.08[民85.08] |
頁 次 | 頁1-6 |
分類號 | 310.153 |
關鍵詞 | 類神經網路; 學習法則; 交流膚參數; |
語 文 | 英文(English) |
中文摘要 | 有關於直接測量交流膚參數,使用類神經網路的方式,比傳統的方式快。因為,只要一種高頻的輸入信號來做線上即時計算。然而,如何來決定那一種類神經網路學習法則,是依據事實的狀況來認定。在本論文中,我們提出各種類神經網路的學習法則,應用於本問題裏。然後,依據各學習法則所對應之各類電腦模擬結果後,我們檢視各方法所得的答案,沒有太大的差異。但是其間計算速度的快慢卻有明顯的差別。所以,我們可結論出類神經網路的學習法則,對演算速度快慢會有重大的影響。 |
英文摘要 | In our previous work, the direct measurement of AC skin parameters hased on a neural net architecture is faster than conventional methods because it uses a real-time, on-line measurement and computation, and requires only one high frequency input signal. In general, deciding whether to use the Widrow learning law or its variants for any problem in neural net depends on the cases. In this paper, we present the various leanings in a neural net architecture for AC skin parameters estimation. After computer simulations, the results show us that the accuracy of estimates for any learning methods are almost no difference. However. the time-consuming of using the Widrow learning is about three times as long as that of using its variant learning. As a result, the variant learning has a significant effect on the performance of AC skin parameters estimation to speed the convergence. |
本系統中英文摘要資訊取自各篇刊載內容。