On explaining the surprising success of reservoir computing forecaster of chaos? The universal machine learning dynamical system with contrast to VAR and DMD
From MaRDI portal
Publication:4983648
DOI10.1063/5.0024890OpenAlexW3049633943MaRDI QIDQ4983648
Publication date: 26 April 2021
Published in: Chaos: An Interdisciplinary Journal of Nonlinear Science (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2008.06530
Related Items
Predicting shallow water dynamics using echo-state networks with transfer learning, Erratum: “On explaining the surprising success of reservoir computing forecaster of chaos? The universal machine learning dynamical system with contrasts to VAR and DMD” [Chaos 31(1), 013108 (2021)], Synchronization of reservoir computing models via a nonlinear controller, Strange properties of linear reservoirs in the infinitely large limit for prediction of continuous-time signals
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Reservoir computing approaches to recurrent neural network training
- A data-driven approximation of the koopman operator: extending dynamic mode decomposition
- Chaotic attractors of an infinite-dimensional dynamical system
- Consistency properties of least squares estimates of autoregressive parameters in ARMA models
- Embedology
- Regular and stochastic motion
- A manifold independent approach to understanding transport in stochastic dynamical systems
- Neural network models. An analysis
- Embedding and approximation theorems for echo state networks
- Deep learning algorithm for data-driven simulation of noisy dynamical system
- An experimental unification of reservoir computing methods
- Applied and Computational Measurable Dynamics
- Applied Koopmanism
- Dynamic mode decomposition of numerical and experimental data
- Spectral analysis of nonlinear flows
- Fading memory and the problem of approximating nonlinear operators with Volterra series
- Delay embedding in the presence of dynamical noise
- A recurrent neural network for modelling dynamical systems
- Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
- Data-driven forecasting of high-dimensional chaotic systems with long short-term memory networks
- Ergodic Theory, Dynamic Mode Decomposition, and Computation of Spectral Properties of the Koopman Operator
- Deterministic Nonperiodic Flow
- Oscillation and Chaos in Physiological Control Systems
- Extended dynamic mode decomposition with dictionary learning: A data-driven adaptive spectral decomposition of the Koopman operator
- Data-Driven Science and Engineering
- On Matching, and Even Rectifying, Dynamical Systems through Koopman Operator Eigenfunctions
- Iterative Krylov Methods for Large Linear Systems
- Path length statistics in reservoir computers
- Causal Network Inference by Optimal Causation Entropy
- MODEL SELECTION, CONFIDENCE AND SCALING IN PREDICTING CHAOTIC TIME-SERIES
- The principle of minimized iterations in the solution of the matrix eigenvalue problem
