Experimental Demonstration of High-Performance Physical Reservoir Computing with Nonlinear Interfered Spin Wave Multi-Detection

TL;DR

This paper experimentally demonstrates a high-performance physical reservoir computing system using nonlinear spin wave interference in yttrium iron garnet, achieving state-of-the-art results in various nonlinear tasks and digit recognition.

Contribution

It provides the first experimental verification of spin wave interference for reservoir computing, showing high performance due to enhanced nonlinearity and memory capacity.

Findings

Achieved the lowest NMSEs for NARMA2 and nonlinear dynamical tasks among experimental reservoirs.

Demonstrated effective hand-written digit recognition using spin wave reservoir computing.

Validated the potential of nonlinear interfered spin waves for high-performance AI hardware.

Abstract

Physical reservoir computing, which is a promising method for the implementation of highly efficient artificial intelligence devices, requires a physical system with nonlinearity, fading memory, and the ability to map in high dimensions. Although it is expected that spin wave interference can perform as highly efficient reservoir computing in some micromagnetic simulations, there has been no experimental verification to date. Herein, we demonstrate reservoir computing that utilizes multidetected nonlinear spin wave interference in an yttrium iron garnet single crystal. The subject computing system achieved excellent performance when used for hand-written digit recognition, second-order nonlinear dynamical tasks, and nonlinear autoregressive moving average (NARMA). It is of particular note that normalized mean square errors (NMSEs) for NARMA2 and second-order nonlinear dynamical tasks were 1.81x10-2 and 8.37x10-5, respectively, which are the lowest figures for any experimental physical reservoir so far reported. Said high performance was achieved with higher nonlinearity and the large memory capacity of interfered spin wave multi-detection.