Home // COGNITIVE 2011, The Third International Conference on Advanced Cognitive Technologies and Applications // View article

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

Authors:
Bassem Khouzam
Hervé Frezza-Buet

Keywords: Dynamic Systems, Recurrent Neural Networks, Self-Organization

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.

Pages: 19 to 24

Copyright: Copyright (c) IARIA, 2011

Publication date: September 25, 2011

Published in: conference

ISSN: 2308-4197

ISBN: 978-1-61208-155-7

Location: Rome, Italy

Dates: from September 25, 2011 to September 30, 2011