Chung-Hua University Repository:Item 987654321/31948
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 8557/14866 (58%)
Visitors : 1406843      Online Users : 1439
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/987654321/31948


    Title: 最小風險神經網路
    Authors: 葉怡成
    Yeh, I-Cheng
    Contributors: 資訊管理學系
    Information Management
    Keywords: 倒傳遞網路;結構風險最小原理;支援向量機;權值衰減
    back;network;structural;minimization;SVM;weight decay
    Date: 2008
    Issue Date: 2014-06-27 01:39:30 (UTC+8)
    Abstract: 本研究提出最小風險神經網路(Minimum Risk Neural Networks, MRNN)，它以倒傳遞神經網路(BPN)為基礎，加入結構風險最小原理的分類間隔最大化的觀念，其目的為了提高BPN分類模型的普遍性，克服過度學習，以提高對驗證範例的準確度。為了證明此網路的性能，本研究以五個經過人為設計的分類問題以及一個實際應用的分類問題來做測試，並與倒傳遞網路做比較。結果證明最小風險神經網路的模型準確度優於倒傳遞網路。本文並比較MRNN與支援向量機的關係，為兩者建立一個統一的理論架構，並證明權值衰減技術
    This study proposed the Minimum Risk Neural Network (MRNN), which is based on back-propagation network (BPN) and combined with the concept of maximization of classification margin of Structural Risk Minimization Theory. Its purpose is to improve the gener
    Appears in Collections:[Department of Information Management] Journal Articles

    Files in This Item:

    File Description SizeFormat
    p_m321_0006.pdf32KbAdobe PDF30View/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