English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 54018/88770 (61%)
造訪人次 : 10547313      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/987654321/37525

    題名: A knowledge-based approach to supervised incremental learning
    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: 1994-06-27
    上傳時間: 2010-04-15 09:45:51 (UTC+8)
    出版者: 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 rule-based connectionist approach in which old knowledge is preserved by bounding weight modifications. In addition, some heuristics are developed for avoiding overtraining of the network and adding new hidden units. The feasibility of this approach is demonstrated for classification problems including the iris and the promoter domains.
    關聯: Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on, vol.3, pp.1793-1798
    DOI: 10.1109/ICNN.1994.374428
    顯示於類別:[資訊工程學系暨研究所] 會議論文


    檔案 描述 大小格式瀏覽次數
    078031901X_3p1793-1798.pdf393KbAdobe PDF555檢視/開啟



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