Incremental backpropagation learning networks

機構典藏 > College of Engineering > Graduate Institute & Department of Computer Science and Information Engineering > Journal Article > Item 987654321/45365

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/45365

Title:	Incremental backpropagation learning networks
Authors:	Fu, Li-min;Hsu, Hui-huang;Principe, Jose C.
Contributors:	淡江大學資訊工程學系
Date:	1996-05
Issue Date:	2010-03-26 19:07:33 (UTC+8)
Publisher:	Piscataway: Institute of Electrical and Electronics Engineers (IEEE)
Abstract:	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
Relation:	IEEE Transactions on Neural Networks 7(3), pp.751-761
DOI:	10.1109/72.501732
Appears in Collections:	[Graduate Institute & Department of Computer Science and Information Engineering] Journal Article

Files in This Item:

File	Description	Size	Format
1045-9227_7(3)p757-761.pdf		563Kb	Adobe PDF	1707	View/Open