Audio Classification with Skyrmion Reservoirs

Abstract

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.

6 pages, 4 figures

References in corpus (1)

• Task-adaptive physical reservoir computing

Cited by in corpus (7)

• Perspective on unconventional computing using magnetic skyrmions
• Handwritten Digit Recognition by Spin Waves in a Skyrmion Reservoir
• Circular motion of non-collinear spin textures in Corbino disks: Dynamics of Néel- versus Bloch-type skyrmions and skyrmioniums
• In-Materia Speech Recognition
• RC circuit based on magnetic skyrmions
• Metrics for spin-based computing
• Correlating on-the-fly Electrical and Optical Skyrmion Readout