PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Block clustering with mixture model : Comparison between different approaches
Mohamed Nadif and Gérard Govaert
In: AMSDA 2005 : International Symposium on Applied Stochastic Models and Data Analysis, 17-20 May 2005, Brest, France.

Abstract

When the data consists of a set of objects described by a set of vari- ables, we have recently proposed a new mixture model which takes into account the block clustering problem on the both sets. In considering this problem under the maximum likelihood and classification maximum likelihood approaches, one can wonder about the performances of the algorithm obtained by block EM, block CEM or by simple uses of the EM and CEM algorithms applied on the both sets separately. The main objective of this paper is to compare these algorithms. Keywords: Block clustering, Mixture model, EM and CEM algorithms.

EPrint Type:Conference or Workshop Item (Talk)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
ID Code:1950
Deposited By:Gérard Govaert
Deposited On:30 December 2005