Learning Mixture Models for Classification with Energy Combination

Chi-Ming Tsou, Chuan Chen and Deng-Yuan Huang
Additional contact information
Chi-Ming Tsou: Lunghwa University of Science and Technology, Taiwan
Chuan Chen: Fu-Jen Catholic University, Taiwan
Deng-Yuan Huang: Fu-Jen Catholic University, Taiwan

Management, 2007, vol. 2, issue 3, 203-214

Abstract: In this article, we propose a technique called Energy Mixture Model (EMM) for classification. EMM is a type of feed-forward neural network that can be used to decide the number of nodes for constructing the hidden layer of neural networks based on the variable clustering method. Additionally, energy combination method is used to generate the recognition pattern as the basis for classification. This approach not only improves the elucidation capability of the model but also discloses the black box of the hidden layer of neural networks. Domain experts can evaluate models built by variable clusters more easily than those built by neural networks.

Keywords: classification; neural network; mutual information; latent class (search for similar items in EconPapers)
Date: 2007
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.fm-kp.si/zalozba/ISSN/1854-4231/2_203-214.pdf full text in English (application/pdf)
http://www.fm-kp.si/zalozba/ISSN/1854-4231/2_273-275.pdf abstract in Slovene (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:mgt:youmng:v:2:y:2007:i:3:p:203-214

Ordering information: This journal article can be ordered from
http://www.mng.fm-kp.si

Access Statistics for this article

Management is currently edited by Klemen Kavcic

More articles in Management from University of Primorska, Faculty of Management Koper Contact information at EDIRC.
Bibliographic data for series maintained by Alen Jezovnik ().