Criticality in Reservoir Computer of Coupled Phase Oscillators

Abstract

Accumulating evidences show that the cerebral cortex is operating near a critical state featured by power-law size distribution of neural avalanche activities, yet evidence of this critical state in artificial neural networks mimicking the cerebral cortex is lacking. Here we design an artificial neural network of coupled phase oscillators and, by the technique of reservoir computing in machine learning, train it for predicting chaos. It is found that when the machine is properly trained, oscillators in the reservoir are synchronized into clusters whose sizes follow a power-law distribution. This feature, however, is absent when the machine is poorly trained. Additionally, it is found that despite the synchronization degree of the original network, once properly trained, the reservoir network is always developed to the same critical state, exemplifying the "attractor" nature of this state in machine learning. The generality of the results is verified in different reservoir models and by different target systems, and it is found that the scaling exponent of the distribution is independent on the reservoir details and the bifurcation parameter of the target system, but is modified when the dynamics of the target system is changed to a different type. The findings shed lights on the nature of machine learning, and are helpful to the design of high-performance machine in physical systems.

8 pages, 4 figures

References in corpus (21)

• Recent Advances in Physical Reservoir Computing: A Review
• Optimal Dynamical Range of Excitable Networks at Criticality
• Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
• Attractor Reconstruction by Machine Learning
• Self-Organized Criticality model for Brain Plasticity
• Landau-Ginzburg theory of cortex dynamics: Scale-free avalanches emerge at the edge of synchronization
• 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
• FitzHugh-Nagumo oscillators on complex networks mimic epileptic-seizure-related synchronization phenomena
• Evidence for quasicritical brain dynamics
• Network Structure Effects in Reservoir Computers
• Good and bad predictions: Assessing and improving the replication of chaotic attractors by means of reservoir computing
• Anticipating synchronization with machine learning
• Do Reservoir Computers Work Best at the Edge of Chaos?
• Dynamical learning of dynamics
• Breaking Symmetries of the Reservoir Equations in Echo State Networks
• Hopf Bifurcation in Mean Field Explains Critical Avalanches in Excitation-Inhibition Balanced Neuronal Networks: A Mechanism for Multiscale Variability
• Transfer learning for nonlinear dynamics and its application to fluid turbulence
• Learn to Synchronize, Synchronize to Learn
• Transfer learning of chaotic systems
• Chaotic Griffiths Phase with Anomalous Lyapunov Spectra in Coupled Map Networks

Cited by in corpus (1)

• Dynamical analysis of a parameter-aware reservoir computer