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.
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal-supelec.archives-ouvertes.fr/hal-00652308
Contributor : Sébastien van Luchene <>
Submitted on : Thursday, December 15, 2011 - 11:46:30 AM
Last modification on : Wednesday, July 31, 2019 - 4:18:03 PM
Long-term archiving on : Friday, November 16, 2012 - 3:41:45 PM

File

KhouzamCognitive11.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00652308, version 1

Collections

Citation

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⟩

Share

Metrics

Record views

341

Files downloads

390