A knowledge-based approach to supervised incremental learning

機構典藏 > College of Engineering > Graduate Institute & Department of Computer Science and Information Engineering > Proceeding > Item 987654321/37525

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/37525

Title:	A knowledge-based approach to supervised incremental learning
Authors:	Fu, Li-min;Hsu, Hui-huang;Principe, Jose C.
Contributors:	淡江大學資訊工程學系
Date:	1994-06-27
Issue Date:	2010-04-15 09:45:51 (UTC+8)
Publisher:	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 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.
Relation:	Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on, vol.3, pp.1793-1798
DOI:	10.1109/ICNN.1994.374428
Appears in Collections:	[Graduate Institute & Department of Computer Science and Information Engineering] Proceeding

Files in This Item:

File	Description	Size	Format
078031901X_3p1793-1798.pdf		393Kb	Adobe PDF	627	View/Open
index.html		0Kb	HTML	285	View/Open