ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Learning with a mutualistic teacher

Gowda, K Chidananda and Krishna, G (1979) Learning with a mutualistic teacher. In: Pattern Recognition, 11 (5-6). pp. 383-390.

Full text not available from this repository. (Request a copy)
Official URL: http://www.sciencedirect.com/science?_ob=ArticleUR...

Abstract

The concept of a “mutualistic teacher” is introduced for unsupervised learning of the mean vectors of the components of a mixture of multivariate normal densities, when the number of classes is also unknown. The unsupervised learning problem is formulated here as a multi-stage quasi-supervised problem incorporating a cluster approach. The mutualistic teacher creates a quasi-supervised environment at each stage by picking out “mutual pairs” of samples and assigning identical (but unknown) labels to the individuals of each mutual pair. The number of classes, if not specified, can be determined at an intermediate stage. The risk in assigning identical labels to the individuals of mutual pairs is estimated. Results of some simulation studies are presented.

Item Type: Journal Article
Additional Information: Copyright of this article belongs to Elsevier Science.
Keywords: Unsupervised learning;Parameter-estimation;Clustering; Mutual nearest neighbourhood;Pattern recognition.
Department/Centre: Division of Electrical Sciences > Computer Science & Automation (Formerly, School of Automation)
Date Deposited: 19 Jan 2010 09:32
Last Modified: 19 Jan 2010 09:32
URI: http://eprints.iisc.ernet.in/id/eprint/24785

Actions (login required)

View Item View Item