Short-wavelength Reverberant Wave Systems for Physical Realization of 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

References in corpus (5)

• Next Generation Reservoir Computing
• Classification of time-domain waveforms using a speckle-based optical reservoir computer
• Sensing Small Changes in a Wave Chaotic Scattering System
• Quantifying Volume Changing Perturbations in a Wave Chaotic System
• Scattering Statistics in Nonlinear Wave Chaotic Systems

Cited by in corpus (4)

• Ultrafast single-channel machine vision based on neuro-inspired photonic computing
• Control of the Scattering Properties of Complex Systems By Means of Tunable Metasurfaces
• Experimental Realization of Anti-Unitary Wave-Chaotic Photonic Topological Insulator Graphs Showing Kramers Degeneracy and Symplectic Ensemble Statistics
• Time Domain Generalization of the Random Coupling Model and Experimental Verification in a Complex Scattering System