English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 54388/89187 (61%)
造訪人次 : 10568590      線上人數 : 21
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋
    請使用永久網址來引用或連結此文件: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/45365


    題名: Incremental backpropagation learning networks
    作者: Fu, Li-min;Hsu, Hui-huang;Principe, Jose C.
    貢獻者: 淡江大學資訊工程學系
    日期: 1996-05
    上傳時間: 2010-03-26 19:07:33 (UTC+8)
    出版者: Piscataway: Institute of Electrical and Electronics Engineers (IEEE)
    摘要: How to learn new knowledge without forgetting old knowledge is a key issue in designing an incremental-learning neural network. In this paper, we present a new incremental learning method for pattern recognition, called the “incremental backpropagation learning network”, which employs bounded weight modification and structural adaptation learning rules and applies initial knowledge to constrain the learning process. The viability of this approach is demonstrated for classification problems including the iris and the promoter domains
    關聯: IEEE Transactions on Neural Networks 7(3), pp.751-761
    DOI: 10.1109/72.501732
    顯示於類別:[資訊工程學系暨研究所] 期刊論文

    文件中的檔案:

    檔案 描述 大小格式瀏覽次數
    1045-9227_7(3)p757-761.pdf563KbAdobe PDF1607檢視/開啟

    在機構典藏中所有的資料項目都受到原著作權保護.

    TAIR相關文章

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - 回饋