Do Reservoir Computers Work Best at the Edge of Chaos?

Abstract

It has been demonstrated that cellular automata had the highest computational capacity at the edge of chaos, the parameter at which their behavior transitioned from ordered to chaotic. This same concept has been applied to reservoir computers; a number of researchers have stated that the highest computational capacity for a reservoir computer is at the edge of chaos, although others have suggested that this rule is not universally true. Because many reservoir computers do not show chaotic behavior but merely become unstable, it is felt that a more accurate term for this instability transition is the "edge of stability"Here I find two examples where the computational capacity of a reservoir computer decreases as the edge of stability is approached; in one case, because generalized synchronization breaks down, and in the other case because the reservoir computer is a poor match to the problem being solved. The edge of stability as an optimal operating point for a reservoir computer is not in general true, although it may be true in some cases.

References in corpus (6)

• Attractor Reconstruction by Machine Learning
• Embedding and Approximation Theorems for Echo State Networks
• Using a reservoir computer to learn chaotic attractors, with applications to chaos synchronisation and cryptography
• Rapid Time Series Prediction with a Hardware-Based Reservoir Computer
• Chaos on compact manifolds: Differentiable synchronizations beyond the Takens theorem
• Testing Dynamical System Variables for Reconstruction

Cited by in corpus (17)

• Dynamical phase transitions in quantum reservoir computing
• Perspective on unconventional computing using magnetic skyrmions
• Optimizing Memory in Reservoir Computers
• Robust Forecasting using Predictive Generalized Synchronization in Reservoir Computing
• Feedback-driven quantum reservoir computing for time-series analysis
• Catch-22s of reservoir computing
• A photonic complex perceptron for ultrafast data processing
• Machine Learning Potential of a Single Pendulum
• Time Shifts to Reduce the Size of Reservoir Computers
• Criticality in Reservoir Computer of Coupled Phase Oscillators
• Reservoir Computers with Random and Optimized Time-Shifts
• Predicting high-dimensional heterogeneous time series employing generalized local states
• How more data can hurt: Instability and regularization in next-generation reservoir computing
• Neuronal correlations shape the scaling behavior of memory capacity and nonlinear computational capability of reservoir recurrent neural networks
• An introduction to reservoir computing
• Phase transitions from linear to nonlinear information processing in neural networks
• Optimal quantum reservoir learning in proximity to universality