Skip to Main content Skip to Navigation
Journal articles

Distributed recurrent self-organization for tracking the state of non-stationary partially observable dynamical systems

Bassem Khouzam 1 Hervé Frezza-Buet 1
1 IMS - Equipe Information, Multimodalité et Signal
UMI2958 - Georgia Tech - CNRS [Metz], SUPELEC-Campus Metz
Abstract : In this paper, a distributed recurrent self-organizing architecture is presented. It can extract the current state of a dynamical system from the sequence of the recent observations provided by this system, even if they are ambiguous. The recurrent network is an adaptation of RecSOM to the context of the simulation of large scale distributed neural architectures, since it relies on a strictly local fine-grained computation. The experiments show the ability of the recurrent architecture to capture the states, but also exhibit some unexpected dynamical effects, like some instabilities of the learned mappings. The presented architecture addresses the cognitive ability to set up representations from sequences at a mesoscopic level. At that intermediate level, between cognition and neurons simulation, some complex dynamics is unveiled. It needs to be identified and understood in order to bridge the gap between neuronal activities and high level cognition.
Document type :
Journal articles
Complete list of metadatas

https://hal-supelec.archives-ouvertes.fr/hal-00771662
Contributor : Sébastien van Luchene <>
Submitted on : Wednesday, January 9, 2013 - 10:40:20 AM
Last modification on : Wednesday, September 16, 2020 - 10:43:37 AM

Identifiers

Collections

Citation

Bassem Khouzam, Hervé Frezza-Buet. Distributed recurrent self-organization for tracking the state of non-stationary partially observable dynamical systems. Biologically Inspired Cognitive Architectures, 2013, 3, pp.87-104. ⟨10.1016/j.bica.2012.11.001⟩. ⟨hal-00771662⟩

Share

Metrics

Record views

612