Echo State Networks trained by Tikhonov least squares are approximators of ergodic dynamical systems
Authors:
- Allen G. HartAHAllen G. Hart
- James L. HookJHJames L. Hook
- Jonathan H.P. DawesJDJonathan H.P. Dawes
- 1 July 2021
- journal article
- research article
- Published by Elsevier in Physica D: Nonlinear Phenomena
- Vol. 421
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- Engineering and Physical Sciences Research Council
This publication has 25 references indexed in Scilit:
- Re-visiting the echo state propertyNeural Networks, 2012
- Functional identification of biological neural networks using reservoir adaptation for point processesJournal of Computational Neuroscience, 2009
- Short-term stock price prediction based on echo state networksExpert Systems with Applications, 2009
- Learning grammatical structure with Echo State NetworksNeural Networks, 2007
- Automatic speech recognition using a predictive echo state network classifierNeural Networks, 2007
- Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on PerturbationsNeural Computation, 2002
- The rate of convergence in ergodic theoremsRussian Mathematical Surveys, 1996
- Generalized Synchronization, Predictability, and Equivalence of Unidirectionally Coupled Dynamical SystemsPhysical Review Letters, 1996
- Dynamical systems with generalized hyperbolic attractors: hyperbolic, ergodic and topological propertiesErgodic Theory and Dynamical Systems, 1992
- Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networksNeural Networks, 1990