A systematic exploration of reservoir computing for forecasting complex spatiotemporal dynamics
A reservoir computer (RC) is a type of recurrent neural network architecture with
demonstrated success in the prediction of spatiotemporally chaotic dynamical systems. A …
demonstrated success in the prediction of spatiotemporally chaotic dynamical systems. A …
Learning spatiotemporal chaos using next-generation reservoir computing
WAS Barbosa, DJ Gauthier - Chaos: An Interdisciplinary Journal of …, 2022 - pubs.aip.org
Forecasting the behavior of high-dimensional dynamical systems using machine learning
requires efficient methods to learn the underlying physical model. We demonstrate …
requires efficient methods to learn the underlying physical model. We demonstrate …
Echo state network and classical statistical techniques for time series forecasting: A review
Forecasting is an extensive field of study, which tries to avoid injuries, diseases, and
damages but also can help in energy production, finance investments, etc. Two mathematics …
damages but also can help in energy production, finance investments, etc. Two mathematics …
Catch-22s of reservoir computing
Y Zhang, SP Cornelius - Physical Review Research, 2023 - APS
Reservoir computing (RC) is a simple and efficient model-free framework for forecasting the
behavior of nonlinear dynamical systems from data. Here, we show that there exist …
behavior of nonlinear dynamical systems from data. Here, we show that there exist …
Learning unseen coexisting attractors
Reservoir computing is a machine learning approach that can generate a surrogate model
of a dynamical system. It can learn the underlying dynamical system using fewer trainable …
of a dynamical system. It can learn the underlying dynamical system using fewer trainable …
Physical reservoir computing using finitely-sampled quantum systems
The paradigm of reservoir computing exploits the nonlinear dynamics of a physical reservoir
to perform complex time-series processing tasks such as speech recognition and …
to perform complex time-series processing tasks such as speech recognition and …
Controlling chaotic maps using next-generation reservoir computing
In this work, we combine nonlinear system control techniques with next-generation reservoir
computing, a best-in-class machine learning approach for predicting the behavior of …
computing, a best-in-class machine learning approach for predicting the behavior of …
Reservoir computing with superconducting electronics
The rapidity and low power consumption of superconducting electronics makes them an
ideal substrate for physical reservoir computing, which commandeers the computational …
ideal substrate for physical reservoir computing, which commandeers the computational …
Shallow univariate relu networks as splines: Initialization, loss surface, hessian, and gradient flow dynamics
Understanding the learning dynamics and inductive bias of neural networks (NNs) is
hindered by the opacity of the relationship between NN parameters and the function …
hindered by the opacity of the relationship between NN parameters and the function …
Learn one size to infer all: Exploiting translational symmetries in delay-dynamical and spatiotemporal systems using scalable neural networks
We design scalable neural networks adapted to translational symmetries in dynamical
systems, capable of inferring untrained high-dimensional dynamics for different system …
systems, capable of inferring untrained high-dimensional dynamics for different system …