Chung-Hua University Repository:Item 987654321/32229
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 8557/14866 (58%)
Visitors : 1990457      Online Users : 1301
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
    Home ‧ Login ‧ Upload ‧ Help ‧ About ‧ Administer Goto mobile version


    Please use this identifier to cite or link to this item: http://chur.chu.edu.tw/handle/987654321/32229


    Title: 複合轉換函數神經網路
    Authors: 葉怡成
    Yeh, I-Cheng
    Contributors: 資訊管理學系
    Information Management
    Keywords: 倒傳遞神經網路;半徑基神經網路;轉換函數;雙彎曲函數;高斯型函數
    BPN;RBFN;transformation;function;Gaussian function
    Date: 2007
    Issue Date: 2014-06-27 01:48:06 (UTC+8)
    Abstract: 傳統的倒傳遞網路(BPN)的隱藏層大都採取雙彎曲轉換函數處理單元，傳統的徑向基底函數網路(RBFN)的隱藏層大都採取高斯型轉換函數處理單元，這二種架構各有優缺點，適合不同類型的問題。為結合這兩種架構的優點，本文提出複合轉換函數神經網路(Hybrid Transfer Function Neural Networks, HTFN)，並推導出其學習規則。此網路在同一個隱藏層中同時包含雙彎曲與高斯型轉換函數的處理單元。為證明此一架構優於傳統的只含雙彎曲轉換函數或只含高斯型轉換函數處理單元的架構，本研究以五個人為
    Traditional back-propagation network (BPN) uses Sigmoid function as transformation function of hidden units; on the other hand, radial basis function network (RBFN) uses Gaussian function as transformation function. These two kinds of structure have their
    Appears in Collections:[Department of Information Management] Journal Articles

    Files in This Item:

    File Description SizeFormat
    p_m321_0046.pdf34KbAdobe PDF116View/Open


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

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