Towards an effective multi-map self organizing recurrent neural network

Denis Baheux 1 Jérémy Fix 1 Hervé Frezza-Buet 1
1 IMS - Equipe Information, Multimodalité et Signal
UMI2958 - Georgia Tech - CNRS [Metz], SUPELEC-Campus Metz
Abstract : This paper presents a multi-map joint self-organizing architecture able to represent non-markovian temporal sequences. The proposed architecture is inspired by previous works based on dynamic neural fields. It provides a faster and easier to handle architecture making it easier to scale to higher dimensional machine learning problems.
Type de document :
Communication dans un congrès
European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2014, Bruges, Belgium. pp.201-206, 2014, ESANN 2014 proceedings. 〈https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2014-126.pdf〉
Liste complète des métadonnées

https://hal-supelec.archives-ouvertes.fr/hal-01104724
Contributeur : Sébastien Van Luchene <>
Soumis le : lundi 19 janvier 2015 - 10:17:39
Dernière modification le : jeudi 5 avril 2018 - 12:30:24

Identifiants

  • HAL Id : hal-01104724, version 1

Collections

Citation

Denis Baheux, Jérémy Fix, Hervé Frezza-Buet. Towards an effective multi-map self organizing recurrent neural network. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2014, Bruges, Belgium. pp.201-206, 2014, ESANN 2014 proceedings. 〈https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2014-126.pdf〉. 〈hal-01104724〉

Partager

Métriques

Consultations de la notice

119