Publication type: Conference paper
Type of review: Peer review (abstract)
Title: Echo state network with chaos noise for time series prediction
Authors: Uwate, Yoko
Schüle, Martin
Ott, Thomas
Noshio, Yoshifumi
et. al: No
Proceedings: Proceedings of the 2020 International Symposium on Nonlinear Theory and its Applications
Page(s): 274
Conference details: International Symposium on Nonlinear Theory and its Applications (NOLTA), Okinawa, Japan, 16–19 November 2020
Issue Date: 16-Nov-2020
Language: English
Subjects: Time series prediction; Echo state network
Subject (DDC): 006: Special computer methods
Abstract: In this study, performance of chaos noise injected to Echo State Network for time series prediction is investigated. For the evaluation of the chaos noise, two parameters of the logistic map are selected to produce different features as intermittency chaos and fully developed chaos. By computer simulations, it is confirmed that the three-periodic intermittency chaos noise is better perfor- mance than the fully developed chaos noise for time series prediction.
Fulltext version: Published version
License (according to publishing contract): Licence according to publishing contract
Departement: Life Sciences and Facility Management
Organisational Unit: Institute of Computational Life Sciences (ICLS)
Appears in collections:Publikationen Life Sciences und Facility Management

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.