教師資料查詢 | 類別: 會議論文 | 教師: 許輝煌 Hsu Hui-huang (瀏覽個人網頁)

標題:A knowledge-based approach to supervised incremental learning
學年82
學期2
發表日期1994/06/27
作品名稱A knowledge-based approach to supervised incremental learning
作品名稱(其他語言)
著者Fu, Li-min; Hsu, Hui-huang; Principe, Jose C.
作品所屬單位淡江大學資訊工程學系
出版者Institute of Electrical and Electronics Engineers (IEEE)
會議名稱Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
會議地點Orlando, FL, USA
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.
關鍵字
語言英文
收錄於
會議性質
校內研討會地點
研討會時間19940627~19940702
通訊作者
國別美國
公開徵稿
出版型式
出處Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on, vol.3, pp.1793-1798
相關連結
Google+ 推薦功能,讓全世界都能看到您的推薦!