elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Reducing network size and improving prediction stability of reservoir computing

Haluszczynski, Alexander and Aumeier, Jonas and herteux, Joschka and Räth, Christoph (2020) Reducing network size and improving prediction stability of reservoir computing. Chaos, 30, 063136. American Institute of Physics (AIP). doi: 10.1063/5.0006869. ISSN 1054-1500.

[img] PDF - Published version
2MB

Official URL: https://doi.org/10.1063/5.0006869

Abstract

Reservoir computing is a very promising approach for the prediction of complex nonlinear dynamical systems. Besides capturing the exact short-term trajectories of nonlinear systems, it has also proved to reproduce its characteristic long-term properties very accurately. However, predictions do not always work equivalently well. It has been shown that both short- and long-term predictions vary significantly among different random realizations of the reservoir. In order to gain an understanding on when reservoir computing works best, we investigate some differential properties of the respective realization of the reservoir in a systematic way. We find that removing nodes that correspond to the largest weights in the output regression matrix reduces outliers and improves overall prediction quality. Moreover, this allows to effectively reduce the network size and, therefore, increase computational efficiency. In addition, we use a nonlinear scaling factor in the hyperbolic tangent of the activation function. This adjusts the response of the activation function to the range of values of the input variables of the nodes. As a consequence, this reduces the number of outliers significantly and increases both the short- and long-term prediction quality for the nonlinear systems investigated in this study. Our results demonstrate that a large optimization potential lies in the systematical refinement of the differential reservoir properties for a given dataset.

Item URL in elib:https://elib.dlr.de/135323/
Document Type:Article
Title:Reducing network size and improving prediction stability of reservoir computing
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Haluszczynski, AlexanderLMU MünchenUNSPECIFIED
Aumeier, JonasJonas.Aumeier (at) dlr.deUNSPECIFIED
herteux, Joschkajoschka.herteux (at) dlr.deUNSPECIFIED
Räth, ChristophChristoph.Raeth (at) dlr.deUNSPECIFIED
Date:2020
Journal or Publication Title:Chaos
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
Volume:30
DOI :10.1063/5.0006869
Page Range:063136
Publisher:American Institute of Physics (AIP)
ISSN:1054-1500
Status:Published
Keywords:complex systems, nonlinear time series, prediction, machine learning, reservoir computing
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Research under Space Conditions
DLR - Research area:Raumfahrt
DLR - Program:R FR - Research under Space Conditions
DLR - Research theme (Project):R - Komplexe Plasmen / Data analysis (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Materials Physics in Space
Deposited By: Räth, Christoph
Deposited On:22 Jun 2020 11:54
Last Modified:17 Jun 2021 03:00

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.