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 en
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 USA
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

機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/37525 )

機構典藏連結