Nonlinear spatiotemporal dynamics in magnetic dipole systems for physical reservoir computing
Nonlinear Dynamics · 2026-03 · 114 (6)
DOI: 10.1007/s11071-026-12291-4 ↗Kurz gefasst
Fachartikel in der Zeitschrift Nonlinear Dynamics, online erschienen am 19.03.2026. Verfasst von Liangshu He und 6 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
To address the challenges of physical interpretability and scalability in artificial neural networks, physical reservoir computing (PRC) has emerged as a promising research direction in contemporary machine learning. PRC tackles these challenges by leveraging simple and efficient physical systems to emulate neural network dynamics. In this work, we develop a theoretical dynamic model of coupled magnetic dipoles driven by an external magnetic field and systematically analyze its dynamic behaviors. We employed this model to construct a standard physical reservoir computing architecture, and revealed the mechanism of magnetic dipole system for computing. Subsequently, the computational performance is evaluated using regression and classification benchmarks. Our results demonstrate that the models’ rich nonlinear dynamic responses provide a robust foundation for achieving high accuracy in both chaotic time-series prediction and spoken digit recognition. The proposed contactless and nonlocal coupling architecture offers valuable theoretical insights for the advancement of PRC hardware development.
Zitieren
APA
He, L., Jin, Y., Edelstein, S., García, P. D., Rabczuk, T., Zhuang, X., & Torrent, D. (2026). Nonlinear spatiotemporal dynamics in magnetic dipole systems for physical reservoir computing. Nonlinear Dynamics, 114(6). https://doi.org/10.1007/s11071-026-12291-4
Vancouver
He L, Jin Y, Edelstein S, García PD, Rabczuk T, Zhuang X, et al. Nonlinear spatiotemporal dynamics in magnetic dipole systems for physical reservoir computing. Nonlinear Dynamics. 2026;114(6). doi:10.1007/s11071-026-12291-4
BibTeX
@article{He2026,
author = {He, Liangshu and Jin, Yabin and Edelstein, Shulamit and García, Pedro David and Rabczuk, Timon and Zhuang, Xiaoying and Torrent, Dani},
title = {Nonlinear spatiotemporal dynamics in magnetic dipole systems for physical reservoir computing},
journal = {Nonlinear Dynamics},
year = {2026},
volume = {114},
number = {6},
doi = {10.1007/s11071-026-12291-4}
}
EUVIMED