Handwritten Digit Recognition by Spin Waves in a Skyrmion Reservoir

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.

References in corpus (8)

• Physical reservoir computing -- An introductory perspective
• Magnetic Skyrmions for Unconventional Computing
• Brownian reservoir computing realized using geometrically confined skyrmions
• Pattern recognition with neuromorphic computing using magnetic-field induced dynamics of skyrmions
• Reservoir Computing with Spin Waves in Skyrmion Crystal
• Perspective on unconventional computing using magnetic skyrmions
• Audio Classification with Skyrmion Reservoirs
• Step-like dependence of memory function on pulse width in spintronics reservoir computing

Cited by in corpus (4)

• Bimerons create bimerons: proliferation and aggregation induced by currents and magnetic fields
• Controlling Skyrmion Lattices via Strain: Elongation, Tilting, and Collapse Mechanisms
• Metrics for spin-based computing
• Reservoir computing by thin film embedded with magnetic impurities