Harnessing spatiotemporal transformation in magnetic domains for nonvolatile physical reservoir computing
Science Advances · 2025-01-10 · 11 (2)
DOI: 10.1126/sciadv.adr5262 ↗At a glance
Journal article in Science Advances, published on 2025-01-10. Written by Jing Zhou and 6 co-authors. Institution: Institute of Materials Research and Engineering (IMRE), Agency for Science Technology and Research (A*STAR), 2 Fusionopolis Way, #08-03 Innovis, Sing…. Cited 22 times so far (Crossref); 72 references. The full text is freely available in PubMed Central.
Abstract (original language)
Combining physics with computational models is increasingly recognized for enhancing the performance and energy efficiency in neural networks. Physical reservoir computing uses material dynamics of physical substrates for temporal data processing. Despite the ease of training, building an efficient reservoir remains challenging. Here, we explore beyond the conventional delay-based reservoirs by exploiting the spatiotemporal transformation in all-electric spintronic devices. Our nonvolatile spintronic reservoir effectively transforms the history dependence of reservoir states to the path dependence of domains. We configure devices triggered by different pulse widths as neurons, creating a reservoir featured by strong nonlinearity and rich interconnections. Using a small reservoir of merely 14 physical nodes, we achieved a high recognition rate of 0.903 in written digit recognition and a low error rate of 0.076 in Mackey-Glass time series prediction on a proof-of-concept printed circuit board. This work presents a promising route of nonvolatile physical reservoir computing, which is adaptable to the larger memristor family and broader physical neural networks.
Authors and institutions
- Institute of Materials Research and Engineering (IMRE), Agency for Science Technology and Research (A*STAR), 2 Fusionopolis Way, #08-03 Innovis, Singapore 138634, Republic of Singapore.
- Key Laboratory of Brain-like Neuromorphic Devices and Systems of Hebei Province, Key Laboratory of Optoelectronic Information Materials of Hebei Province, Hebei University, Baoding 071002, China.
ORCID profiles: Jing Zhou, Jikang Xu, Lisen Huang, Sherry Lee Koon Yap, Shaohai Chen, Xiaobing Yan, Sze Ter Lim
Cite
APA
Zhou, J., Xu, J., Huang, L., Yap, S. L. K., Chen, S., Yan, X., & Ter Lim, S. (2025). Harnessing spatiotemporal transformation in magnetic domains for nonvolatile physical reservoir computing. Science Advances, 11(2). https://doi.org/10.1126/sciadv.adr5262
Vancouver
Zhou J, Xu J, Huang L, Yap SLK, Chen S, Yan X, et al. Harnessing spatiotemporal transformation in magnetic domains for nonvolatile physical reservoir computing. Science Advances. 2025;11(2). doi:10.1126/sciadv.adr5262
BibTeX
@article{Zhou2025,
author = {Zhou, Jing and Xu, Jikang and Huang, Lisen and Yap, Sherry Lee Koon and Chen, Shaohai and Yan, Xiaobing and Ter Lim, Sze},
title = {Harnessing spatiotemporal transformation in magnetic domains for nonvolatile physical reservoir computing},
journal = {Science Advances},
year = {2025},
volume = {11},
number = {2},
doi = {10.1126/sciadv.adr5262}
}
EUVIMED