Quantifying the Computational Capability of a Nanomagnetic Reservoir Computing Platform with Emergent Magnetization Dynamics

TL;DR

This paper demonstrates how to optimize nanomagnetic reservoir computing platforms using hyperparameter tuning and multi-measure outputs, leading to improved digit recognition performance.

Contribution

It introduces a phenomenological model for optimizing magnetic nano-ring reservoirs for classification tasks through hyperparameter tuning and multi-measure outputs.

Findings

Reservoirs can be optimized via hyperparameter tuning using magnetic fields.

Task-independent metrics correlate with classification performance.

Multi-measure outputs enhance computational capabilities.

Abstract

Devices based on arrays of interconnected magnetic nano-rings with emergent magnetization dynamics have recently been proposed for use in reservoir computing applications, but for them to be computationally useful it must be possible to optimise their dynamical responses. Here, we use a phenomenological model to demonstrate that such reservoirs can be optimised for classification tasks by tuning hyperparameters that control the scaling and input rate of data into the system using rotating magnetic fields. We use task-independent metrics to assess the rings' computational capabilities at each set of these hyperparameters and show how these metrics correlate directly to performance in spoken and written digit recognition tasks. We then show that these metrics, and performance in tasks, can be further improved by expanding the reservoir's output to include multiple, concurrent measures of the ring arrays magnetic states.