Reconstruction of Complex Dynamical Systems from Time Series using Reservoir Computing

Research output: Chapter in Book/Conference paperConference paper

175 Downloads (Pure)

Abstract

We investigate the capacity of reservoir computers to reconstruct the dynamics of a network of chaotic oscillators via the observation of its multivariate time series. The reservoir is itself a structured echo-state network which receives the current observations as inputs, and is trained to produce the next observations as outputs. We study the performance of this scheme and its dependence on the separation of the inputs, modularity of the reservoir network, and observability of the system. We observe optimal performance with a segregated input structure and extremely modular network.
Original languageEnglish
Title of host publication2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings
PublisherIEEE, Institute of Electrical and Electronics Engineers
ISBN (Electronic)978-1-7281-0397-6
ISBN (Print)978-1-7281-0398-3
DOIs
Publication statusPublished - 1 May 2019
Event2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Sapporo, Japan
Duration: 26 May 201929 May 2019

Publication series

NameProceedings - IEEE International Symposium on Circuits and Systems
Volume2019-May
ISSN (Print)0271-4310

Conference

Conference2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019
CountryJapan
CitySapporo
Period26/05/1929/05/19

Fingerprint

dynamical systems
modularity
echoes
oscillators
output

Cite this

Jüngling, T., Lymburn, T., Stemler, T., Corrêa, D., Walker, D., & Small, M. (2019). Reconstruction of Complex Dynamical Systems from Time Series using Reservoir Computing. In 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings [8702137] (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2019-May). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ISCAS.2019.8702137
Jüngling, Thomas ; Lymburn, Thomas ; Stemler, Thomas ; Corrêa, Débora ; Walker, David ; Small, Michael. / Reconstruction of Complex Dynamical Systems from Time Series using Reservoir Computing. 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. IEEE, Institute of Electrical and Electronics Engineers, 2019. (Proceedings - IEEE International Symposium on Circuits and Systems).
@inproceedings{2dfe5f00ed2e4574918332662fed7c99,
title = "Reconstruction of Complex Dynamical Systems from Time Series using Reservoir Computing",
abstract = "We investigate the capacity of reservoir computers to reconstruct the dynamics of a network of chaotic oscillators via the observation of its multivariate time series. The reservoir is itself a structured echo-state network which receives the current observations as inputs, and is trained to produce the next observations as outputs. We study the performance of this scheme and its dependence on the separation of the inputs, modularity of the reservoir network, and observability of the system. We observe optimal performance with a segregated input structure and extremely modular network.",
keywords = "Reservoirs, Neurons, Time series analysis, Oscillators, Training, Task analysis",
author = "Thomas J{\"u}ngling and Thomas Lymburn and Thomas Stemler and D{\'e}bora Corr{\^e}a and David Walker and Michael Small",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/ISCAS.2019.8702137",
language = "English",
isbn = "978-1-7281-0398-3",
series = "Proceedings - IEEE International Symposium on Circuits and Systems",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
booktitle = "2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings",
address = "United States",

}

Jüngling, T, Lymburn, T, Stemler, T, Corrêa, D, Walker, D & Small, M 2019, Reconstruction of Complex Dynamical Systems from Time Series using Reservoir Computing. in 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings., 8702137, Proceedings - IEEE International Symposium on Circuits and Systems, vol. 2019-May, IEEE, Institute of Electrical and Electronics Engineers, 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019, Sapporo, Japan, 26/05/19. https://doi.org/10.1109/ISCAS.2019.8702137

Reconstruction of Complex Dynamical Systems from Time Series using Reservoir Computing. / Jüngling, Thomas; Lymburn, Thomas; Stemler, Thomas; Corrêa, Débora; Walker, David; Small, Michael.

2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. IEEE, Institute of Electrical and Electronics Engineers, 2019. 8702137 (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2019-May).

Research output: Chapter in Book/Conference paperConference paper

TY - GEN

T1 - Reconstruction of Complex Dynamical Systems from Time Series using Reservoir Computing

AU - Jüngling, Thomas

AU - Lymburn, Thomas

AU - Stemler, Thomas

AU - Corrêa, Débora

AU - Walker, David

AU - Small, Michael

PY - 2019/5/1

Y1 - 2019/5/1

N2 - We investigate the capacity of reservoir computers to reconstruct the dynamics of a network of chaotic oscillators via the observation of its multivariate time series. The reservoir is itself a structured echo-state network which receives the current observations as inputs, and is trained to produce the next observations as outputs. We study the performance of this scheme and its dependence on the separation of the inputs, modularity of the reservoir network, and observability of the system. We observe optimal performance with a segregated input structure and extremely modular network.

AB - We investigate the capacity of reservoir computers to reconstruct the dynamics of a network of chaotic oscillators via the observation of its multivariate time series. The reservoir is itself a structured echo-state network which receives the current observations as inputs, and is trained to produce the next observations as outputs. We study the performance of this scheme and its dependence on the separation of the inputs, modularity of the reservoir network, and observability of the system. We observe optimal performance with a segregated input structure and extremely modular network.

KW - Reservoirs

KW - Neurons

KW - Time series analysis

KW - Oscillators

KW - Training

KW - Task analysis

UR - http://www.scopus.com/inward/record.url?scp=85066792697&partnerID=8YFLogxK

U2 - 10.1109/ISCAS.2019.8702137

DO - 10.1109/ISCAS.2019.8702137

M3 - Conference paper

SN - 978-1-7281-0398-3

T3 - Proceedings - IEEE International Symposium on Circuits and Systems

BT - 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings

PB - IEEE, Institute of Electrical and Electronics Engineers

ER -

Jüngling T, Lymburn T, Stemler T, Corrêa D, Walker D, Small M. Reconstruction of Complex Dynamical Systems from Time Series using Reservoir Computing. In 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. IEEE, Institute of Electrical and Electronics Engineers. 2019. 8702137. (Proceedings - IEEE International Symposium on Circuits and Systems). https://doi.org/10.1109/ISCAS.2019.8702137