Cottrell, M. and Ibbou, S. (1995). Multiple correspondence analysis of a crosstabulation matrix using the Kohonen algorithm. In Proceedings of ESANN'95, pages 27--32. Editions D Facto, Bruxelles. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Kohonen Maps Versus Vector Quantization for Data Analysis - de Bodt, Verleysen, Cottrell (1997) Self-citation (Cottrell) (Correct)
....an exponent between the underlying density of vectors and centroids before and after VQ and propose to modify the algorithm to remedy to this problem . this non unity exponent is known as the magnification coefficient [7] Although different, this coefficient can be related to Lloyd s work [10]. We will try to see to which extend these arguments are pertinent regarding to definitions, well known theoretical properties and simulations on simple examples. 211 2. Definitions and algorithms A continuous space , of dimension d, has a continuous probability density function (pdf) f(x) ....
....algorithm ensures that, after learning, close points in the input space (according to an Euclidean distance measure for example) will be associated to the same centroid or to close centroids on the line or grid. This topological property is of most interest in many applications (see e.g. [9,10]) but this point will not be discussed here. We will focus our discussion on two aspects of the Kohonen algorithm: the vector quantization property, and the link between the distribution of centroids and the initial distribution fix) During the learning phase, the Kohonen algorithm uses ....
Cottrell M., Ibbou S., Multiple correspondence analysis of a crosstabulaiion matrix using the Kohonen algorithm, Proc. ESANN'95, M.Verleysen Ed., Editions D Facto, Bruxelles, 27-32, 1995.
Kohonen Maps Versus Vector Quantization for Data Analysis - de Bodt, Verleysen, Cottrell (1997) Self-citation (Cottrell) (Correct)
....exists an exponent between the underlying density of vectors and centroids before and after VQ and propose to modify the algorithm to remedy to this problem . this non unity exponent is known as the magnification coefficient [7] Although different, this coefficient can be related to Lloyd s work [10]. European Symposium on Artificial Neural Networks 1997, Bruges (Belgium) April 1997, D Facto publications (Brussels) ISBN 2 9600049 7 3. 212 We will try to see to which extend these arguments are pertinent regarding to definitions, well known theoretical properties and simulations on simple ....
....algorithm ensures that, after learning, close points in the input space W (according to an Euclidean distance measure for example) will be associated to the same centroid or to close centroids on the line or grid. This topological property is of most interest in many applications (see e.g. [9,10]) but this point will not be discussed here. We will focus our discussion on two aspects of the Kohonen algorithm : the vector quantization property, and the link between the distribution of centroids and the initial distribution f(x) During the learning phase, the Kohonen algorithm uses ....
Cottrell M., Ibbou S., Multiple correspondence analysis of a crosstabulation matrix using the Kohonen algorithm, Proc. ESANN'95, M.Verleysen Ed., Editions D Facto, Bruxelles, 27-32, 1995.
Bibliography of Self-Organizing Map (SOM) Papers.. - Merja Oja, Samuel.. (2002) (Correct)
No context found.
Cottrell, M. and Ibbou, S. (1995). Multiple correspondence analysis of a crosstabulation matrix using the Kohonen algorithm. In Proceedings of ESANN'95, pages 27--32. Editions D Facto, Bruxelles.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC