Reservoir Computing with Noise

Abstract

This paper investigates in detail the effects of noise on the performance of reservoir computing. We focus on an application in which reservoir computers are used to learn the relationship between different state variables of a chaotic system. We recognize that noise can affect differently the training and testing phases. We find that the best performance of the reservoir is achieved when the strength of the noise that affects the input signal in the training phase equals the strength of the noise that affects the input signal in the testing phase. For all the cases we examined, we found that a good remedy to noise is to low-pass filter the input and the training/testing signals; this typically preserves the performance of the reservoir, while reducing the undesired effects of noise.

References in corpus (10)

• Recent Advances in Physical Reservoir Computing: A Review
• Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
• Using reservoir computers to distinguish chaotic signals
• Rapid Time Series Prediction with a Hardware-Based Reservoir Computer
• Delayed Dynamical Systems: Networks, Chimeras and Reservoir Computing
• PAM-4 Transmission at 1550nm using Photonic Reservoir Computing Post-processing
• Fundamental aspects of noise in analog-hardware neural networks
• Using synchronization of chaos to identify the dynamics of unknown systems
• Creating New Chaotic Signals with Reservoir Computers
• Adding Filters to Improve Reservoir Computer Performance

Cited by in corpus (4)

• Synchronizing Chaos using Reservoir Computing
• Random forests for detecting weak signals and extracting physical information: a case study of magnetic navigation
• Denoising and Reconstruction of Nonlinear Dynamics using Truncated Reservoir Computing
• Optimizing the Network Topology of a Linear Reservoir Computer