2021/11/29 by Ian T. Vidamour, Vidamour, Ian T, Matthew O. A. Ellis +27 · 1 citation
Computer Science · Engineering · #Advanced Memory and Neural Computing #Emerging Technologies (cs.ET) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Mesoscale and Nanoscale Physics (cond-mat.mes-hall) #Neural Networks and Applications #Neural Networks and Reservoir Computing
paper · pdf · doi:10.48550/arxiv.2111.14603
openalex publication_date 2021/11/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.