Handwritten Digit Recognition by Spin Waves in a Skyrmion Reservoir

TL;DR

This paper demonstrates that a skyrmion lattice in a thin magnetic film can serve as an effective reservoir for handwritten digit recognition, achieving high accuracy through enhanced nonlinear data transformation.

Contribution

It introduces a novel reservoir computing approach using magnetic skyrmions, showing superior performance over traditional echo state networks without complex fabrication.

Findings

Achieved over 88% recognition accuracy, outperforming baseline models.

Identified enhanced nonlinearity from spin wave interference as key to performance.

Skyrmion-based reservoirs require only static magnetic fields, simplifying fabrication.

Abstract

By performing numerical simulations for the handwritten digit recognition task, we demonstrate that a magnetic skyrmion lattice confined in a thin-plate magnet possesses high capability of reservoir computing. We obtain a high recognition rate of more than 88%, higher by about 10% than a baseline taken as the echo state network model. We find that this excellent performance arises from enhanced nonlinearity in the transformation which maps the input data onto an information space with higher dimensions, carried by interferences of spin waves in the skyrmion lattice. Because the skyrmions require only application of static magnetic field instead of nanofabrication for their creation in contrast to other spintronics reservoirs, our result consolidates the high potential of skyrmions for application to reservoir computing devices.