Look and Feel What and How Recurrent Self-Organizing Maps Learn

This paper introduces representations and measurements for revealing the inner self-organization that occurs in a 1D recurrent self-organizing map. Experiments show the incredible richness and robustness of an extremely simple architecture when it extracts hidden states of the HMM that feeds it with ambiguous and noisy inputs.

Mots clés

Recurrent self-organizing map Sequence processing Hidden markov models

Domaines

Réseau de neurones [cs.NE]

Fichier principal

wsom-19-Fix-FrezzaBuet.pdf (1.87 Mo)

Origine	Fichiers produits par l'(les) auteur(s)

Hervé Frezza-Buet : Connectez-vous pour contacter le contributeur

https://hal.science/hal-02120117

Soumis le : mardi 17 mars 2020-11:13:13

Dernière modification le : lundi 11 septembre 2023-17:41:19

Archivage à long terme le : jeudi 18 juin 2020-13:55:19

Dates et versions

hal-02120117 , version 1 (17-03-2020)

Identifiants

HAL Id : hal-02120117 , version 1
DOI : 10.1007/978-3-030-19642-4_1

Citer

Jérémy Fix, Hervé Frezza-Buet. Look and Feel What and How Recurrent Self-Organizing Maps Learn. Advances in Self-Organizing Maps, Learning Vector Quantization, Clustering and Data Visualization, WSOM 19, 976, pp.3-12, 2020, Advances in Intelligent Systems and Computing, 978-3-030-19641-7. ⟨10.1007/978-3-030-19642-4_1⟩. ⟨hal-02120117⟩

Exporter

BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite

Collections

CNRS INRIA CENTRALESUPELEC UNIV-LORRAINE LORIA LORIA-AIS HUB-IA

289 Consultations

297 Téléchargements