Consistency in Echo-State Networks
Dynamical Systems
2019-02-20 v1
Abstract
Consistency is an extension to generalized synchronization which quantifies the degree of functional dependency of a driven nonlinear system to its input. We apply this concept to echo-state networks, which are an artificial-neural network version of reservoir computing. Through a replica test we measure the consistency levels of the high-dimensional response, yielding a comprehensive portrait of the echo-state property.
Keywords
Cite
@article{arxiv.1901.07729,
title = {Consistency in Echo-State Networks},
author = {Thomas Lymburn and Alexander Khor and Thomas Stemler and Débora C. Corrêa and Michael Small and Thomas Jüngling},
journal= {arXiv preprint arXiv:1901.07729},
year = {2019}
}
Comments
9 pages, 9 figures, The following article has been accepted by Chaos: An Interdisciplinary Journal of Nonlinear Science. After it is published, it will be found at https://aip.scitation.org/journal/cha