Prediction for nonlinear time series by improved deep echo state network based on reservoir states reconstruction

Prediction for nonlinear time series by improved deep echo state network based on reservoir states reconstruction

Abstract With the aim to enhance prediction accuracy for nonlinear time series, this paper put forward an improved deep Echo State Network based on reservoir states reconstruction driven by a Self-Normalizing Activation (SNA) function as the replacement for the traditional Hyperbolic tangent activat...

Full description

Bibliographic Details
Main Authors: Qiufeng Yu, Hui Zhao, Li Teng, Li Li, Ansar Yasar, Stéphane Galland
Format: Article
Language:English
Published: Springer 2024-02-01
Series:Autonomous Intelligent Systems
Subjects:
Echo state networks
Time series prediction
Reconstruction model
Self-normalizing activation function
Reservoir computing
Online Access:https://doi.org/10.1007/s43684-023-00057-3

Similar Items

Similar Items