1. NCCU Academic Hub
  2. 理學院
  3. 應用數學系
  4. 學位論文
Please use this identifier to cite or link to this item: https://ah.lib.nccu.edu.tw/handle/140.119/88732
DC FieldValueLanguage
dc.contributor.advisor蔡隆義zh_TW
dc.contributor.advisorTsai, Long Yien_US
dc.contributor.author林明璋zh_TW
dc.contributor.authorLin, Ming Jangen_US
dc.creator林明璋zh_TW
dc.creatorLin, Ming Jangen_US
dc.date1994en_US
dc.date.accessioned2016-04-29T08:32:12Z-
dc.date.available2016-04-29T08:32:12Z-
dc.date.issued2016-04-29T08:32:12Z-
dc.identifierB2002003900en_US
dc.identifier.urihttp://nccur.lib.nccu.edu.tw/handle/140.119/88732-
dc.description碩士zh_TW
dc.description國立政治大學zh_TW
dc.description應用數學系zh_TW
dc.description81155003zh_TW
dc.description.abstract　　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　　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\r\nAbstract\r\nContents\r\nSection 1　Introduction-----1\r\nSection 2　Recurrent Neural Network-----3\r\n　　2.1　Structure Neural Network-----3\r\n　　2.2　Recurrent Back-Propagation-----6\r\n　　2.3　Adjoint Equation and Teacher Forcing-----8\r\n　　　　2.3.1　Teacher Forcing-----8\r\n　　　　2.3.2　Adjoint Equation-----9\r\n　　2.4　Adaptive Time-Delay-----16\r\nSection 3　Convergence Analysis-----22\r\nSection 4　Simulation-----27\r\n　　4.1　Circular Trajectory-----28\r\n　　4.2　Figure Eight-----34\r\n　　4.3　Convergence Analysis-----39\r\nSection 5　Conclusion-----43\r\nReferences-----44zh_TW
dc.source.urihttp://thesis.lib.nccu.edu.tw/record/#B2002003900en_US
dc.subject遞迴式神經網路zh_TW
dc.subject遞迴式倒傳遞法zh_TW
dc.subject自伴方程式zh_TW
dc.subject強制教授法zh_TW
dc.subject可調式時間遲延法zh_TW
dc.subjectRecurrent neural networksen_US
dc.subjectRecurrent Back-Propagationen_US
dc.subjectAdjoint Equationen_US
dc.subjectTeacher Forcingen_US
dc.subjectAdaptive Time Delayen_US
dc.title動態遞迴式神經網路之研究zh_TW
dc.titleResearch on Dynamic Recurrent Neural Networken_US
dc.typethesisen_US
item.fulltextWith Fulltext-
item.openairecristypehttp://purl.org/coar/resource_type/c_46ec-
item.grantfulltextopen-
item.openairetypethesis-
item.cerifentitytypePublications-
Appears in Collections:學位論文
Files in This Item:
File SizeFormat
index.html115 BHTML2View/Open
Show simple item record

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.