A novel competitive learning algorithm for the parametric classification with Gaussian distributions

Wen Jyi Hwang; Bo Yuan Ye; Chin Tsai Lin

doi:10.1016/S0167-8655(00)00004-0

A novel competitive learning algorithm for the parametric classification with Gaussian distributions

Wen Jyi Hwang, Bo Yuan Ye, Chin Tsai Lin

研究成果: 雜誌貢獻 › 期刊論文 › 同行評審

5 引文斯高帕斯（Scopus）

摘要

A competitive learning algorithm for the parametric classification of Gaussian sources is presented in this letter. The algorithm iteratively estimates the mean and prior probability of each class during the training. Bayes rule is then used for classification based on the estimated information. Simulation results show that the proposed algorithm outperforms k-means and LVQ algorithms for the parametric classification.

原文	英語
頁（從 - 到）	375-380
頁數	6
期刊	Pattern Recognition Letters
卷	21
發行號	5
DOIs	https://doi.org/10.1016/S0167-8655(00)00004-0
出版狀態	已發佈 - 2000 5月
對外發佈	是

ASJC Scopus subject areas

軟體
訊號處理
電腦視覺和模式識別
人工智慧

存取文件

10.1016/S0167-8655(00)00004-0

其它文件與鏈接

引用此

@article{86ed17aef64044c1af29dea1c1902c9a,

title = "A novel competitive learning algorithm for the parametric classification with Gaussian distributions",

abstract = "A competitive learning algorithm for the parametric classification of Gaussian sources is presented in this letter. The algorithm iteratively estimates the mean and prior probability of each class during the training. Bayes rule is then used for classification based on the estimated information. Simulation results show that the proposed algorithm outperforms k-means and LVQ algorithms for the parametric classification.",

keywords = "Competitive learning, Maximum likelihood estimation, Neural networks, Parametric classification, Pattern recognition",

author = "Hwang, {Wen Jyi} and Ye, {Bo Yuan} and Lin, {Chin Tsai}",

year = "2000",

month = may,

doi = "10.1016/S0167-8655(00)00004-0",

language = "English",

volume = "21",

pages = "375--380",

journal = "Pattern Recognition Letters",

issn = "0167-8655",

publisher = "Elsevier",

number = "5",

}

TY - JOUR

T1 - A novel competitive learning algorithm for the parametric classification with Gaussian distributions

AU - Hwang, Wen Jyi

AU - Ye, Bo Yuan

AU - Lin, Chin Tsai

PY - 2000/5

Y1 - 2000/5

N2 - A competitive learning algorithm for the parametric classification of Gaussian sources is presented in this letter. The algorithm iteratively estimates the mean and prior probability of each class during the training. Bayes rule is then used for classification based on the estimated information. Simulation results show that the proposed algorithm outperforms k-means and LVQ algorithms for the parametric classification.

AB - A competitive learning algorithm for the parametric classification of Gaussian sources is presented in this letter. The algorithm iteratively estimates the mean and prior probability of each class during the training. Bayes rule is then used for classification based on the estimated information. Simulation results show that the proposed algorithm outperforms k-means and LVQ algorithms for the parametric classification.

KW - Competitive learning

KW - Maximum likelihood estimation

KW - Neural networks

KW - Parametric classification

KW - Pattern recognition

UR - http://www.scopus.com/inward/record.url?scp=0033734671&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033734671&partnerID=8YFLogxK

U2 - 10.1016/S0167-8655(00)00004-0

DO - 10.1016/S0167-8655(00)00004-0

M3 - Article

AN - SCOPUS:0033734671

VL - 21

SP - 375

EP - 380

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

IS - 5

ER -

A novel competitive learning algorithm for the parametric classification with Gaussian distributions

摘要

ASJC Scopus subject areas

存取文件

其它文件與鏈接

指紋

引用此