Do Reservoir Computers Work Best at the Edge of Chaos?

2020/12/01 by Thomas L. Carroll, T. L. Carroll · 11 citations
Computer Science · Engineering · Physics and Astronomy · #Advanced Memory and Neural Computing #Chaos control and synchronization #Neural Networks and Reservoir Computing #cs.NE #nlin.CD

paper · pdf · doi:10.1063/5.0038163

openalex publication_date 2020/12/01 · arxiv created 2020/12/02 · openalex created_date 2020/12/07 · arxiv updated 2021/02/03 · openalex updated_date 2026/07/28

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.

Cited by

• Optimal quantum reservoir learning in proximity to universality
• Photonic neural networks at the edge of spatiotemporal chaos in multimode fibers
• Reservoir computing with large valid prediction time for the Lorenz system
• Reservoir computing approaches to unsupervised concept drift detection in dynamical systems
• Phase transitions from linear to nonlinear information processing in neural networks
• Reservoir Computing with a single Josephson junction
• Neuronal correlations shape the scaling behavior of memory capacity and nonlinear computational capability of reservoir recurrent neural networks
• A photonic complex perceptron for ultrafast data processing
• Optimizing Memory in Reservoir Computers
• Dynamical Phase Transitions in Quantum Reservoir Computing
• Boosting Reservoir Computing with Brain-inspired Adaptive Dynamics

Related

• Mutual Information and the Edge of Chaos in Reservoir Computers
• Dynamics, Computation, and the "Edge of Chaos": A Re-Examination
• Beyond the Edge of Chaos: Stability-Expressivity Transfer in Reservoir Forecasting
• Minimal Model for Reservoir Computing
• Tuning the activation function to optimize the forecast horizon of a reservoir computer