Reservoir computing using a spin-wave delay line active ring resonator

TL;DR

This paper introduces a novel reservoir computing system based on a spin-wave active ring resonator, leveraging nonlinear spin wave dynamics for processing time series data with potential advantages in speed and integration.

Contribution

It presents a new implementation of reservoir computing using a magnetic thin film delay line in an active ring resonator, demonstrating its feasibility for time series tasks.

Findings

Successfully implemented reservoir computing with spin waves.

Achieved performance on short term memory and parity check tasks.

Showed potential for integrated, high-speed neuromorphic computing.

Abstract

The authors demonstrate the use of a propagating spin waves for implementing a reservoir computing architecture. The proposed concept utilises an active ring resonator comprising a magnetic thin film delay line integrated into a feedback loop. These systems exhibit strong nonlinearity and delayed response behaviour, two important properties required for an effective reservoir computing implementation. In a simple design, we exploit the nonlinear damping of spin waves at different feedback gains to inject input data into the active ring resonator and use a microwave diode to read out the amplitude of the spin waves circulating in the ring. We employ two baseline tasks, namely the short term memory and parity check tasks, to evaluate the suitability of this architecture for processing time series data.