Please use this identifier to cite or link to this item: https://ah.nccu.edu.tw/handle/140.119/88732


Title: 動態遞迴式神經網路之研究
Research on Dynamic Recurrent Neural Network
Authors: 林明璋
Lin, Ming Jang
Contributors: 蔡隆義
Tsai, Long Yi
林明璋
Lin, Ming Jang
Keywords: 遞迴式神經網路
遞迴式倒傳遞法
自伴方程式
強制教授法
可調式時間遲延法
Recurrent neural networks
Recurrent Back-Propagation
Adjoint Equation
Teacher Forcing
Adaptive Time Delay
Date: 1994
Issue Date: 2016-04-29 16:32:12 (UTC+8)
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。
  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.
Description: 碩士
國立政治大學
應用數學系
81155003
Source URI: http://thesis.lib.nccu.edu.tw/record/#B2002003900
Data Type: thesis
Appears in Collections:[應用數學系] 學位論文

Files in This Item:

File SizeFormat
index.html0KbHTML159View/Open


All items in 學術集成 are protected by copyright, with all rights reserved.


社群 sharing