Audio Classification with Skyrmion Reservoirs

Abstract

Physical reservoir computing is a computational paradigm that enables spatiotemporal pattern recognition to be performed directly in matter. The use of physical matter leads the way toward energy‐efficient devices capable of solving machine learning problems without having to build a system of millions of interconnected neurons. Proposed herein is a high‐performance “skyrmion mixture reservoir” that implements the reservoir computing model with multidimensional inputs. This implementation solves spoken digit classification tasks with an overall model accuracy of 97.4% and a < 1% word error ratethe best performance ever reported for in materio reservoir computers. Due to the quality of the results and the low‐power properties of magnetic texture reservoirs, it is evident that skyrmion fabrics are a compelling candidate for reservoir computing.

300‐Times‐Increased Diffusive Skyrmion Dynamics and Effective Pinning Reduction by Periodic Field Excitation

“…On the other hand, in Brownian reservoir computing, skyrmion diffusion serves as automatic reset mechanism and is necessary to overcome device imperfections. Even though skyrmion diffusion on the reported time scales [ 6 ] has recently been experimentally demonstrated to successfully enable Brownian reservoir computing, [ 34 ] a faster operation of such devices or especially processing input signals on shorter time scales—such as for the newly proposed audio recognition [ 36 ] —is only enabled by higher skyrmion diffusion speeds. Unless strongly driven, the skyrmion dynamics has been found to be heavily impacted by size‐dependent pinning effects that induce a non‐flat effective energy landscape.…”