A LEARNING-MODEL OF THE FEATURE-DETECTING CELLS FOR UNSUPERVISED PATTERN-CLASSIFICATION

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Electrical Engineering > journal & Dissertation > Item 987654321/29405

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/29405

Title:	A LEARNING-MODEL OF THE FEATURE-DETECTING CELLS FOR UNSUPERVISED PATTERN-CLASSIFICATION
Authors:	WANG,WJ;LEE,DL
Contributors:	電機工程研究所
Keywords:	RECOGNITION
Date:	1994
Issue Date:	2010-06-29 20:23:56 (UTC+8)
Publisher:	中央大學
Abstract:	A modified neural network unsupervised learning scheme by the feature-detecting cell is proposed. We improve the performance in learning categories by adding a modulation system and a competing system to the conventional feature-detecting cell model. With the aid of the modultion system and the competing system, the cluster prototype which is closet to the input pattern will win the competitions and a winner dominated learning will be controlled by the properly assigned bias values. The proposed model has the following features: it guarantees the corresponding feature-detecting cell of each input pattern to be formed regardless of the initial weights and the duplication (of the feature-detecting cells formation for each sampled input pattern) can be reduced.
Relation:	PATTERN RECOGNITION LETTERS
Appears in Collections:	[Graduate Institute of Electrical Engineering] journal & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	431	View/Open

社群 sharing