Reservoir Computing with Random Skyrmion Textures

Abstract

The Reservoir Computing (RC) paradigm posits that sufficiently complex physical systems can be used to massively simplify pattern recognition tasks and nonlinear signal prediction. This work demonstrates how random topological magnetic textures present sufficiently complex resistance responses for the implementation of RC as applied to A/C current pulses. In doing so, we stress how the applicability of this paradigm hinges on very general dynamical properties which are satisfied by a large class of physical systems where complexity can be put to computational use. By harnessing the complex resistance response exhibited by random magnetic skyrmion textures and using it to demonstrate pattern recognition, we explain how spintronically accessible magnetic systems offer an advantage in the search for an ideal reservoir computer. The low-power properties of compact skyrmion fabrics, coupled with their CMOS integrability operating on similar length and timescales, open the door for their RC employment geared towards industrial application.