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

NCU Institutional Repository > 資訊電機學院 > 電機工程研究所 > 期刊論文 > Item 987654321/29405

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/29405

题名:	A LEARNING-MODEL OF THE FEATURE-DETECTING CELLS FOR UNSUPERVISED PATTERN-CLASSIFICATION
作者:	WANG,WJ;LEE,DL
贡献者:	電機工程研究所
关键词:	RECOGNITION
日期:	1994
上传时间:	2010-06-29 20:23:56 (UTC+8)
出版者:	中央大學
摘要:	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.
關聯:	PATTERN RECOGNITION LETTERS
显示于类别:	[電機工程研究所] 期刊論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	462	检视/开启

在NCUIR中所有的数据项都受到原著作权保护.

社群 sharing