Discovering the phase of a dynamical system from a stream of partial observations with a multi-map self-organizing architecture - CentraleSupélec Access content directly
Conference Papers Year : 2011

Discovering the phase of a dynamical system from a stream of partial observations with a multi-map self-organizing architecture

Abstract

This paper presents a self-organizing architecture made of several maps, implementing a recurrent neural network to cope with partial observations of the phase of some dynamical system. The purpose of self-organization is to set up a distributed representation of the actual phase, although the observations received from the system are ambiguous (i.e. the same observation may correspond to distinct phases). The setting up of such a representation is illustrated by experiments, and then the paper concludes on extensions toward adaptive state representations for partially observable Markovian decision processes.
Fichier principal
Vignette du fichier
KhouzamCognitive11.pdf (404.3 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00652308 , version 1 (15-12-2011)

Identifiers

  • HAL Id : hal-00652308 , version 1

Cite

Bassem Khouzam, Hervé Frezza-Buet. Discovering the phase of a dynamical system from a stream of partial observations with a multi-map self-organizing architecture. COGNITIVE 2011, Sep 2011, Rome, Italy. pp.19-24. ⟨hal-00652308⟩
213 View
344 Download

Share

Gmail Facebook X LinkedIn More