Symmetry kills the square in a multifunctional reservoir computer
From MaRDI portal
Publication:5011745
DOI10.1063/5.0055699OpenAlexW3177961110MaRDI QIDQ5011745
Christoph Räth, Joschka Herteux, Vassilios A. Tsachouridis, Andrew Flynn, Andreas Amann
Publication date: 27 August 2021
Published in: Chaos: An Interdisciplinary Journal of Nonlinear Science (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1063/5.0055699
Learning and adaptive systems in artificial intelligence (68T05) Strange attractors, chaotic dynamics of systems with hyperbolic behavior (37D45)
Cites Work
- Embedding and approximation theorems for echo state networks
- Echo state networks trained by Tikhonov least squares are \(L^2(\mu)\) approximators of ergodic dynamical systems
- Echo state networks are universal
- An experimental unification of reservoir computing methods
- Do reservoir computers work best at the edge of chaos?
- Breaking symmetries of the reservoir equations in echo state networks
- Reservoir computing with swarms
- Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
- Deterministic Nonperiodic Flow
- Good and bad predictions: Assessing and improving the replication of chaotic attractors by means of reservoir computing
- Multifunctionality in a reservoir computer
- Invertible generalized synchronization: A putative mechanism for implicit learning in neural systems
This page was built for publication: Symmetry kills the square in a multifunctional reservoir computer
