Potential implementation of Reservoir Computing models based on magnetic skyrmions

TL;DR

This paper explores the potential of using magnetic skyrmions in reservoir computing, highlighting their suitability as physical substrates for recursive neural networks that process spatio-temporal data.

Contribution

It introduces the concept of implementing reservoir computing models using magnetic skyrmions, expanding beyond memristor-based approaches and proposing a new physical platform.

Findings

Skyrmion fabrics can potentially serve as reservoirs for neural networks.

Magnetic skyrmions offer a promising physical basis for reservoir computing.

This approach may enable new hardware implementations of neural networks.

Abstract

Reservoir Computing is a type of recursive neural network commonly used for recognizing and predicting spatio-temporal events relying on a complex hierarchy of nested feedback loops to generate a memory functionality. The Reservoir Computing paradigm does not require any knowledge of the reservoir topology or node weights for training purposes and can therefore utilize naturally existing networks formed by a wide variety of physical processes. Most efforts prior to this have focused on utilizing memristor techniques to implement recursive neural networks. This paper examines the potential of skyrmion fabrics formed in magnets with broken inversion symmetry that may provide an attractive physical instantiation for Reservoir Computing.