Physical reservoir computing is a computational paradigm that enables spatio-temporal pattern recognition to be performed directly in matter. The use of physical matter leads the way towards energy-efficient devices capable of solving machine learning problems without having to build a system of millions of interconnected neurons. We propose a high performance "skyrmion mixture reservoir" that implements the reservoir computing model with multi-dimensional inputs. We show that our implementation solves spoken digit classification tasks at the nanosecond timescale, with an overall model accuracy of 97.4% and a less that 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, we argue that skyrmion fabrics are a compelling candidate for reservoir computing.
@article{arxiv.2209.13946,
title = {Audio Classification with Skyrmion Reservoirs},
author = {Robin Msiska and Jake Love and Jeroen Mulkers and Jonathan Leliaert and Karin Everschor-Sitte},
journal= {arXiv preprint arXiv:2209.13946},
year = {2025}
}