Rapid Time Series Prediction with a Hardware-Based Reservoir Computer

Abstract

Reservoir computing is a neural network approach for processing time-dependent signals that has seen rapid development in recent years. Physical implementations of the technique using optical reservoirs have demonstrated remarkable accuracy and processing speed at benchmark tasks. However, these approaches require an electronic output layer to maintain high performance, which limits their use in tasks such as time-series prediction, where the output is fed back into the reservoir. We present here a reservoir computing scheme that has rapid processing speed both by the reservoir and the output layer. The reservoir is realized by an autonomous, time-delay, Boolean network configured on a field-programmable gate array. We investigate the dynamical properties of the network and observe the fading memory property that is critical for successful reservoir computing. We demonstrate the utility of the technique by training a reservoir to learn the short- and long-term behavior of a chaotic system. We find accuracy comparable to state-of-the-art software approaches of similar network size, but with a superior real-time prediction rate up to 160 MHz.

References in corpus (7)

• Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
• All-optical Reservoir Computing
• Attractor Reconstruction by Machine Learning
• Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Model
• Reservoir computing with a single time-delay autonomous Boolean node
• Boolean Chaos
• Criticality in Random Threshold Networks: Annealed Approximation and Beyond

Cited by in corpus (27)

• On Explaining the Surprising Success of Reservoir Computing Forecaster of Chaos? The Universal Machine Learning Dynamical System with Contrasts to VAR and DMD
• Forecasting Chaotic Systems with Very Low Connectivity Reservoir Computers
• Gaussian states of continuous-variable quantum systems provide universal and versatile reservoir computing
• Network Structure Effects in Reservoir Computers
• Do Reservoir Computers Work Best at the Edge of Chaos?
• Data-Driven Reduced-Order Modeling of Spatiotemporal Chaos with Neural Ordinary Differential Equations
• Parallel Machine Learning for Forecasting the Dynamics of Complex Networks
• Using Machine Learning to Anticipate Tipping Points and Extrapolate to Post-Tipping Dynamics of Non-Stationary Dynamical Systems
• Efficient Design of Hardware-Enabled Reservoir Computing in FPGAs
• Optimizing Memory in Reservoir Computers
• Reservoir Computing Approach to Quantum State Measurement
• Using reservoir computer to predict and prevent extreme events
• Robust Forecasting using Predictive Generalized Synchronization in Reservoir Computing
• Learning unseen coexisting attractors
• Reservoir Computing with Noise
• Catch-22s of reservoir computing
• Dimension of Reservoir Computers
• Time Shifts to Reduce the Size of Reservoir Computers
• Tackling Sampling Noise in Physical Systems for Machine Learning Applications: Fundamental Limits and Eigentasks
• Model-free prediction of emergence of extreme events in a parametrically driven nonlinear dynamical system by Deep Learning
• Symmetry-Aware Reservoir Computing
• Creating New Chaotic Signals with Reservoir Computers
• Short-wavelength Reverberant Wave Systems for Physical Realization of Reservoir Computing
• Adding Filters to Improve Reservoir Computer Performance
• Stochastic Reservoir Computers
• Practical Trainable Temporal Postprocessor for Multistate Quantum Measurement
• Excitatory/Inhibitory Balance Emerges as a Key Factor for RBN Performance, Overriding Attractor Dynamics