Probabilistic Topological Map and Binary data - Archive ouverte HAL
Communication Dans Un Congrès Année : 2001

Probabilistic Topological Map and Binary data

Résumé

The Self Organizing Map (SOM) proposed by Kohonen is a well known neural model which provides both quantization and clustering of the observation space. In this paper, we adapt the Bernoulli mixture approach to the model of binary topological map and show that using a probabilistic formalism gives rise to better quantization process and classification performances.
Fichier non déposé

Dates et versions

hal-01124637 , version 1 (06-03-2015)

Identifiants

  • HAL Id : hal-01124637 , version 1

Citer

Mustapha Lebbah, C. Chabanon, Sylvie Thiria, Fouad Badran. Probabilistic Topological Map and Binary data. ICANN2001, Jan 2001, X, France. ⟨hal-01124637⟩
44 Consultations
0 Téléchargements

Partager

More