Short term memory in input-driven linear dynamical systems

Authors:
Peter TiňO;Ali Rodan
Affiliations:
School of Computer Science, The University of Birmingham, Birmingham B15 2TT, United Kingdom;King Abdulla II School for Information Technology, The University of Jordan, P.O. Box 11942, Amman, Jordan
Venue:
Neurocomputing
Year:
2013

Citing 3
Cited 0

2007 Special Issue: Learning grammatical structure with Echo State Networks

Neural Networks
Survey: Reservoir computing approaches to recurrent neural network training

Computer Science Review
Minimum Complexity Echo State Network

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.01

Visualization

Abstract

We investigate the relation between two quantitative measures characterizing short term memory in input driven dynamical systems, namely the short term memory capacity (MC) [3] and the Fisher memory curve (FMC) [2]. We show that even though MC and FMC map the memory structure of the system under investigation from two quite different perspectives, for linear input driven dynamical systems they are in fact closely related. In particular, under some assumptions, the two quantities can be interpreted as squared 'Mahalanobis' norms of images of the input vector under the system's dynamics. We also offer a detailed rigorous analysis of the relation between MC and FMC in cases of symmetric and cyclic dynamic couplings.