About the multidimensional competitive learning vector quantization algorithm with constant gain
Bouton, Catherine ; Pagès, Gilles
Ann. Appl. Probab., Tome 7 (1997) no. 1, p. 679-710 / Harvested from Project Euclid
The competitive learning vector quantization (CLVQ) algorithm with constant step $\varepsilon > 0$--also known as the Kohonen algorithm with 0 neighbors--is studied when the stimuli are i.i.d. vectors. Its first noticeable feature is that, unlike the one-dimensional case which has $n!$ absorbing subsets, the CLVQ algorithm is "irreducible on open sets" whenever the stimuli distribution has a path-connected support with a nonempty interior. Then the Doeblin recurrence (or uniform ergodicity) of the algorithm is established under some convexity assumption on the support. Several properties of the invariant probability measure $\nu^{\varepsilon}$ are studied, including support location and absolute continuity with respect to the Lebesgue measure. Finally, the weak limit set of $\nu^{\varepsilon}$ as $\varepsilon \to 0$ is investigated.
Publié le : 1997-08-14
Classification:  Vector quantization,  neural networks,  Markov chain,  uniform ergodicity,  60J20,  60J10,  60F99
@article{1034801249,
     author = {Bouton, Catherine and Pag\`es, Gilles},
     title = {About the multidimensional competitive learning vector
		 quantization algorithm with constant gain},
     journal = {Ann. Appl. Probab.},
     volume = {7},
     number = {1},
     year = {1997},
     pages = { 679-710},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1034801249}
}
Bouton, Catherine; Pagès, Gilles. About the multidimensional competitive learning vector
		 quantization algorithm with constant gain. Ann. Appl. Probab., Tome 7 (1997) no. 1, pp.  679-710. http://gdmltest.u-ga.fr/item/1034801249/