Skip to Main content Skip to Navigation
Conference papers

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.
Document type :
Conference papers
Complete list of metadatas
Contributor : Sébastien van Luchene <>
Submitted on : Monday, January 19, 2015 - 10:17:39 AM
Last modification on : Wednesday, September 16, 2020 - 10:43:37 AM


  • HAL Id : hal-01104724, version 1



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. ⟨hal-01104724⟩



Record views