Skip to Main content Skip to Navigation
Conference papers

Towards an effective multi-map self organizing recurrent neural network

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 metadata
Contributor : Sébastien van Luchene Connect in order to contact the contributor
Submitted on : Monday, January 19, 2015 - 10:17:39 AM
Last modification on : Tuesday, April 27, 2021 - 10:28:04 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⟩



Les métriques sont temporairement indisponibles