Consistency in echo-state networks

Thomas Michael Lymburn, Alexander Joseph Khor, Thomas Stemler, Debora Correa, Michael Small, Thomas Jungling

Research output: Contribution to journalArticle

5 Citations (Scopus)
227 Downloads (Pure)

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.
Original languageEnglish
Article number023118
Pages (from-to)1-9
Number of pages9
JournalChaos: an interdisciplinary journal of nonlinear science
Volume29
Issue number2
DOIs
Publication statusPublished - 11 Feb 2019

Fingerprint

Echo State Network
Nonlinear systems
echoes
Synchronization
Neural networks
Generalized Synchronization
Functional Dependency
Replica
nonlinear systems
replicas
Artificial Neural Network
synchronism
Quantify
High-dimensional
Nonlinear Systems
Computing
Concepts

Cite this

@article{0c5f12d583eb4f84aa4aa6e7b8e01b64,
title = "Consistency in echo-state networks",
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.",
author = "Lymburn, {Thomas Michael} and Khor, {Alexander Joseph} and Thomas Stemler and Debora Correa and Michael Small and Thomas Jungling",
year = "2019",
month = "2",
day = "11",
doi = "10.1063/1.5079686",
language = "English",
volume = "29",
pages = "1--9",
journal = "Chaos",
issn = "1054-1500",
publisher = "ACOUSTICAL SOC AMER AMER INST PHYSICS",
number = "2",

}

Consistency in echo-state networks. / Lymburn, Thomas Michael; Khor, Alexander Joseph; Stemler, Thomas; Correa, Debora; Small, Michael; Jungling, Thomas.

In: Chaos: an interdisciplinary journal of nonlinear science, Vol. 29, No. 2, 023118, 11.02.2019, p. 1-9.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Consistency in echo-state networks

AU - Lymburn, Thomas Michael

AU - Khor, Alexander Joseph

AU - Stemler, Thomas

AU - Correa, Debora

AU - Small, Michael

AU - Jungling, Thomas

PY - 2019/2/11

Y1 - 2019/2/11

N2 - 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.

AB - 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.

U2 - 10.1063/1.5079686

DO - 10.1063/1.5079686

M3 - Article

VL - 29

SP - 1

EP - 9

JO - Chaos

JF - Chaos

SN - 1054-1500

IS - 2

M1 - 023118

ER -