EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Remote training of a reservoir computer via digital twins

Yutaro Sekiguchi iD, Rie Sai, André Röhm iD, Takatomo Mihana iD, Tomoki Yamagami iD, Kazutaka Kanno iD, Atsushi Uchida iD, Ryoichi Horisaki iD

Chaos: An Interdisciplinary Journal of Nonlinear Science · 01.09.2025 · 35 (9)

DOI: 10.1063/5.0273463 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Chaos: An Interdisciplinary Journal of Nonlinear Science, online erschienen am 04.09.2025. Verfasst von Yutaro Sekiguchi und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Physics and Computing, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science, Core Research for Evolutional Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The increasing energy consumption required for information processing has become a significant challenge, leading to growing interest in optical and optoelectronic reservoir computing as a more efficient alternative. Trained reservoir computers are especially suited for low-energy applications near the edge. However, the computational cost of training the reservoir output weights, particularly due to matrix operations, adds potentially unwanted complexity to the architecture. To lift this restriction, we propose a remote training approach using digital twins—virtual models that replicate the behavior of a physical reservoir. In particular, unlike traditional training methods, we do not need to record the reservoir states experimentally for every new task. This allows the physical reservoir to be used continuously for inference without interruptions. We constructed two types of digital twins: a differential equation-based model and a deep neural network (DNN) model. Using the proposed remote training on real experimental data for the Santa-Fe laser time-series task confirmed that both models successfully captured the dynamics of the optoelectronic reservoir, allowing accurate predictions and the export of weights from the digital twin to the real world. The equation-based model achieved higher prediction accuracy than the DNN model, while the DNN model demonstrated greater robustness to variations in hyperparameters. These results demonstrate that digital twins can effectively enable the remote training of reservoir computing systems.

Autor:innen und Institutionen

  • Department of Information Physics and Computing, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan.
  • Department of Information and Computer Sciences, Saitama University, 255 Shimo-okubo, Sakura-ku, Saitama City, Saitama 338-8570, Japan.

ORCID-Profile: Yutaro Sekiguchi, André Röhm, Takatomo Mihana, Tomoki Yamagami, Kazutaka Kanno, Atsushi Uchida, Ryoichi Horisaki

Förderung

  • Japan Society for the Promotion of Science
  • Core Research for Evolutional Science and Technology

Zitieren

APA

Sekiguchi, Y., Sai, R., Röhm, A., Mihana, T., Yamagami, T., Kanno, K., Uchida, A., & Horisaki, R. (2025). Remote training of a reservoir computer via digital twins. Chaos: An Interdisciplinary Journal of Nonlinear Science, 35(9). https://doi.org/10.1063/5.0273463

Vancouver

Sekiguchi Y, Sai R, Röhm A, Mihana T, Yamagami T, Kanno K, et al. Remote training of a reservoir computer via digital twins. Chaos: An Interdisciplinary Journal of Nonlinear Science. 2025;35(9). doi:10.1063/5.0273463

BibTeX
@article{Sekiguchi2025,
  author = {Sekiguchi, Yutaro and Sai, Rie and Röhm, André and Mihana, Takatomo and Yamagami, Tomoki and Kanno, Kazutaka and Uchida, Atsushi and Horisaki, Ryoichi},
  title = {Remote training of a reservoir computer via digital twins},
  journal = {Chaos: An Interdisciplinary Journal of Nonlinear Science},
  year = {2025},
  volume = {35},
  number = {9},
  doi = {10.1063/5.0273463}
}
Kostenlos starten →