Incremental backpropagation learning networks
學年 84
學期 2
出版(發表)日期 1996-05-01
作品名稱 Incremental backpropagation learning networks
作品名稱(其他語言)
著者 Fu, Li-min; Hsu, Hui-huang; Principe, Jose C.
單位 淡江大學資訊工程學系
出版者 Piscataway: Institute of Electrical and Electronics Engineers (IEEE)
著錄名稱、卷期、頁數 IEEE Transactions on Neural Networks 7(3), pp.751-761
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
關鍵字
語言 en
ISSN 1045-9227
期刊性質 國外
收錄於
產學合作
通訊作者
審稿制度
國別 USA
公開徵稿
出版型式 電子版
相關連結

機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/45365 )

機構典藏連結