Short-wavelength Reverberant Wave Systems for Physical Realization of Reservoir Computing

TL;DR

This paper demonstrates how reverberant short wavelength waves can be used to physically implement and enhance reservoir computing systems, improving their computational power through spatial and spectral perturbations in microwave experiments.

Contribution

It introduces a novel physical reservoir computing approach using reverberant short wavelength waves and a method to expand the effective reservoir size via perturbations.

Findings

Reverberant wave sensitivity enhances reservoir computational capacity.

Experimental validation in microwave regime shows improved ML task performance.

The approach is broadly applicable to reverberant wave-based reservoir computing.

Abstract

Machine learning (ML) has found widespread application over a broad range of important tasks. To enhance ML performance, researchers have investigated computational architectures whose physical implementations promise compactness, high-speed execution, physical robustness, and low energy cost. Here, we experimentally demonstrate an approach that uses the high sensitivity of reverberant short wavelength waves for physical realization and enhancement of computational power of a type of ML known as reservoir computing (RC). The potential computation power of RC systems increases with their effective size. We here exploit the intrinsic property of short wavelength reverberant wave sensitivity to perturbations to expand the effective size of the RC system by means of spatial and spectral perturbations. Working in the microwave regime, this scheme is tested experimentally on different ML tasks. Our results indicate the general applicability of reverberant wave-based implementations of RC and of our effective reservoir size expansion technique