Using neural networks for controlling chaos

P. M. Alsing, A. Gavrielides, V. Kovanis

Research output: Contribution to journalArticle

36 Citations (Scopus)

Abstract

A feed-forward backpropagating neutral network is trained to achieve and maintain control of the unstable periodic orbits embedded in a chaotic attractor. The controlling algorithms used for training the network are based on the now standard scheme developed by Ott, Grebogi, and Yorke [Phys. Rev. Lett. 64, 1196 (1990)], including variants that utilize previous perturbations and/or delayed time-series data.

Original languageEnglish
Pages (from-to)1225-1231
Number of pages7
JournalPhysical Review E - Statistical, Nonlinear, and Soft Matter Physics
Volume49
Issue number2
DOIs
Publication statusPublished - 1994
Externally publishedYes

Fingerprint

Neutral Networks
Controlling Chaos
Feedforward Networks
Chaotic Attractor
Time Series Data
Periodic Orbits
chaos
Unstable
Neural Networks
Perturbation
education
orbits
perturbation
Training
Standards

ASJC Scopus subject areas

  • Mathematical Physics
  • Physics and Astronomy(all)
  • Condensed Matter Physics
  • Statistical and Nonlinear Physics

Cite this

Using neural networks for controlling chaos. / Alsing, P. M.; Gavrielides, A.; Kovanis, V.

In: Physical Review E - Statistical, Nonlinear, and Soft Matter Physics, Vol. 49, No. 2, 1994, p. 1225-1231.

Research output: Contribution to journalArticle

Alsing, P. M. ; Gavrielides, A. ; Kovanis, V. / Using neural networks for controlling chaos. In: Physical Review E - Statistical, Nonlinear, and Soft Matter Physics. 1994 ; Vol. 49, No. 2. pp. 1225-1231.
@article{26c912e58c1c417ca5cb8129ee2aa2e9,
title = "Using neural networks for controlling chaos",
abstract = "A feed-forward backpropagating neutral network is trained to achieve and maintain control of the unstable periodic orbits embedded in a chaotic attractor. The controlling algorithms used for training the network are based on the now standard scheme developed by Ott, Grebogi, and Yorke [Phys. Rev. Lett. 64, 1196 (1990)], including variants that utilize previous perturbations and/or delayed time-series data.",
author = "Alsing, {P. M.} and A. Gavrielides and V. Kovanis",
year = "1994",
doi = "10.1103/PhysRevE.49.1225",
language = "English",
volume = "49",
pages = "1225--1231",
journal = "Physical review. E",
issn = "2470-0045",
publisher = "American Physical Society",
number = "2",

}

TY - JOUR

T1 - Using neural networks for controlling chaos

AU - Alsing, P. M.

AU - Gavrielides, A.

AU - Kovanis, V.

PY - 1994

Y1 - 1994

N2 - A feed-forward backpropagating neutral network is trained to achieve and maintain control of the unstable periodic orbits embedded in a chaotic attractor. The controlling algorithms used for training the network are based on the now standard scheme developed by Ott, Grebogi, and Yorke [Phys. Rev. Lett. 64, 1196 (1990)], including variants that utilize previous perturbations and/or delayed time-series data.

AB - A feed-forward backpropagating neutral network is trained to achieve and maintain control of the unstable periodic orbits embedded in a chaotic attractor. The controlling algorithms used for training the network are based on the now standard scheme developed by Ott, Grebogi, and Yorke [Phys. Rev. Lett. 64, 1196 (1990)], including variants that utilize previous perturbations and/or delayed time-series data.

UR - http://www.scopus.com/inward/record.url?scp=0000280659&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0000280659&partnerID=8YFLogxK

U2 - 10.1103/PhysRevE.49.1225

DO - 10.1103/PhysRevE.49.1225

M3 - Article

VL - 49

SP - 1225

EP - 1231

JO - Physical review. E

JF - Physical review. E

SN - 2470-0045

IS - 2

ER -