| dc.contributor.advisor | 蔡隆義 | zh_TW |
| dc.contributor.advisor | Tsai, Long Yi | en_US |
| dc.contributor.author (Authors) | 林明璋 | zh_TW |
| dc.contributor.author (Authors) | Lin, Ming Jang | en_US |
| dc.creator (作者) | 林明璋 | zh_TW |
| dc.creator (作者) | Lin, Ming Jang | en_US |
| dc.date (日期) | 1994 | en_US |
| dc.date.accessioned | 29-Apr-2016 16:32:12 (UTC+8) | - |
| dc.date.available | 29-Apr-2016 16:32:12 (UTC+8) | - |
| dc.date.issued (上傳時間) | 29-Apr-2016 16:32:12 (UTC+8) | - |
| dc.identifier (Other Identifiers) | B2002003900 | en_US |
| dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/88732 | - |
| dc.description (描述) | 碩士 | zh_TW |
| dc.description (描述) | 國立政治大學 | zh_TW |
| dc.description (描述) | 應用數學系 | zh_TW |
| dc.description (描述) | 81155003 | zh_TW |
| dc.description.abstract (摘要) | 此篇論文，主要是討論遞迴式神經網路。在文中，我們將架構一個單層的神經網路結構。並利用三種不同的學習法則來套用此架構。我們也做了圓軌跡和圖形８的模擬，以及討論了此架構的收斂性。 | zh_TW |
| dc.description.abstract (摘要) | Our task in this paper is to discuss the Recurrent Neural Network. We construct a singal layer neural network and apply three different learning rules to simulate circular trajectory and figure eight. Also, we present the proof of convergence. | en_US |
| dc.description.tableofcontents | 中文摘要 Abstract Contents Section 1 Introduction-----1 Section 2 Recurrent Neural Network-----3 2.1 Structure Neural Network-----3 2.2 Recurrent Back-Propagation-----6 2.3 Adjoint Equation and Teacher Forcing-----8 2.3.1 Teacher Forcing-----8 2.3.2 Adjoint Equation-----9 2.4 Adaptive Time-Delay-----16 Section 3 Convergence Analysis-----22 Section 4 Simulation-----27 4.1 Circular Trajectory-----28 4.2 Figure Eight-----34 4.3 Convergence Analysis-----39 Section 5 Conclusion-----43 References-----44 | zh_TW |
| dc.source.uri (資料來源) | http://thesis.lib.nccu.edu.tw/record/#B2002003900 | en_US |
| dc.subject (關鍵詞) | 遞迴式神經網路 | zh_TW |
| dc.subject (關鍵詞) | 遞迴式倒傳遞法 | zh_TW |
| dc.subject (關鍵詞) | 自伴方程式 | zh_TW |
| dc.subject (關鍵詞) | 強制教授法 | zh_TW |
| dc.subject (關鍵詞) | 可調式時間遲延法 | zh_TW |
| dc.subject (關鍵詞) | Recurrent neural networks | en_US |
| dc.subject (關鍵詞) | Recurrent Back-Propagation | en_US |
| dc.subject (關鍵詞) | Adjoint Equation | en_US |
| dc.subject (關鍵詞) | Teacher Forcing | en_US |
| dc.subject (關鍵詞) | Adaptive Time Delay | en_US |
| dc.title (題名) | 動態遞迴式神經網路之研究 | zh_TW |
| dc.title (題名) | Research on Dynamic Recurrent Neural Network | en_US |
| dc.type (資料類型) | thesis | en_US |
