ASIA unversity:Item 310904400/111215
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 94286/110023 (86%)
Visitors : 21657518      Online Users : 453
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version


    Please use this identifier to cite or link to this item: http://asiair.asia.edu.tw/ir/handle/310904400/111215


    Title: 具高計算效率之遞迴神經網路系統實現
    Authors: 程冠穎
    Contributors: 光電與通訊學系碩士在職專班
    Keywords: 遞迴神經網路、狀態空間、計算效率、極點靈敏度、recurrent neural network、state-space、computational efficiency、pole sensitivity
    Date: 2018
    Issue Date: 2018-07-25 07:14:27 (UTC+0)
    Publisher: 亞洲大學
    Abstract: 本論文提出一種具有高計算效率之狀態空間遞迴式神經網路,我們所提出的神經網路架構為區域回授的狀態空間架構。我們所提出的神經網路主要考量在定點式數位裝置中實現。該高運算效率狀態空間結構主要基於極點靈敏度最佳化的前提下進行合成,相較於傳統的最佳化濾波器架構,每個取樣時間需要(n+1)2個乘法運算,本論文所提出的架構僅需要4n+1個乘法運算,n為狀態空間階數。在使用倒傳遞學習演算法下,我們所提出的架構在RNN架構下與傳統最佳化結構有近似的學習效果,但卻可有效大幅降低運算負擔,最後我們以數值案例驗證了本論文所提方法的有效性。
    In this thesis, a high computational efficiency recurrent neural network (RNN) with state-space realizations is proposed. The proposed RNN is local feedback. We con-sider that the RNN is implemented in fixed-point digital devices. The high compu-tational efficiency state-space is synthesized based on pole sensitivity measure minimization. In contrast to the conventional optimal structures, the proposed structure requires only 4n+1 multiplications in every sample time rather than (n+1)2 multiplications in the conventional ones, where n is the order of the state-space systems. By using back propagation learning algorithm, the proposed structure is with similar performances comparing with the conventional optimal structures, but can significantly be with lower computational burden. Finally, numerical examples are performed to illustrate the effectiveness of the proposed approach.
    Appears in Collections:[Department of Photonics and Communication Engineering] Theses & dissertations

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML405View/Open


    All items in ASIAIR are protected by copyright, with all rights reserved.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback