Incremental backpropagation learning networks

淡江大學機構典藏 > 工學院 > 資訊工程學系暨研究所 > 期刊論文 > Item 987654321/45365

請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/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.pdf		563Kb	Adobe PDF	1706	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