Next Generation Reservoir Computing

1 code implementation • 14 Jun 2021 • Daniel J. Gauthier, Erik Bollt, Aaron Griffith, Wendson A. S. Barbosa

Reservoir computing is a best-in-class machine learning algorithm for processing information generated by dynamical systems using observed time-series data.

Time Series Time Series Analysis

Symmetry-Aware Reservoir Computing

no code implementations • 30 Jan 2021 • Wendson A. S. Barbosa, Aaron Griffith, Graham E. Rowlands, Luke C. G. Govia, Guilhem J. Ribeill, Minh-Hai Nguyen, Thomas A. Ohki, Daniel J. Gauthier

For the parity task, our symmetry-aware RC obtains zero error using an exponentially reduced neural network and training data, greatly speeding up the time to result and outperforming hand crafted artificial neural networks.

Forecasting Chaotic Systems with Very Low Connectivity Reservoir Computers

no code implementations • 1 Oct 2019 • Aaron Griffith, Andrew Pomerance, Daniel J. Gauthier

We explore the hyperparameter space of reservoir computers used for forecasting of the chaotic Lorenz '63 attractor with Bayesian optimization.

Bayesian Optimization

Rapid Time Series Prediction with a Hardware-Based Reservoir Computer

no code implementations • 19 Jul 2018 • Daniel Canaday, Aaron Griffith, Daniel Gauthier

Reservoir computing is a neural network approach for processing time-dependent signals that has seen rapid development in recent years.

Time Series Time Series Prediction