Speedup of an all-optical delay-based reservoir computer via input rate increase and bandwidth enhancement
Chaos: An Interdisciplinary Journal of Nonlinear Science · 01.07.2025 · 35 (7)
DOI: 10.1063/5.0273485 ↗Kurz gefasst
Fachartikel in der Zeitschrift Chaos: An Interdisciplinary Journal of Nonlinear Science, online erschienen am 18.07.2025. Verfasst von Mirko Goldmann und 5 weiteren Autor:innen. Beteiligte Einrichtung: Instituto de Física Interdisciplinar y Sistemas Complejos (IFISC), UIB-CSIC, UIB Campus, Palma de Mallorca E-07122, Spain. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: Ministerio de Ciencia e Innovación, H2020 Marie Skłodowska-Curie Actions, HORIZON EUROPE Marie Sklodowska-Curie Actions.
Abstract (Originalsprache)
We demonstrate the acceleration of an all-optical delay-based reservoir computer (RC) for time-series prediction. The RC system comprises a semiconductor laser with delayed optical feedback, driven by an injection laser modulated with a time-multiplexed input signal. We numerically and experimentally investigate how node separation, the emission frequency of the lasers, and feedback strength influence prediction performance, with a particular focus on the Mackey–Glass chaotic time series. Numerical simulations, based on the Lang–Kobayashi rate equations, reveal that a small node separation of 12 ps yields superior performance by exploiting bandwidth enhancement. Critically, we find that reducing an input period well below the delay time, and optimizing the number of virtual nodes, significantly increases the inference rate to 0.417 GSa/s, a 10-fold improvement over processing at the rate of the delay time. In experimental realizations, we can confirm these findings, showing good agreement with numerical predictions. This speedup also enhances energy efficiency, reducing the energy per inference from 26.5 to 2.6 nJ in our proof-of-concept settings. The results highlight the importance of tuning time scales inherent to both the physical substrate and the computational task for optimized, high-speed, and energy-efficient reservoir computing.
Autor:innen und Institutionen
- Instituto de Física Interdisciplinar y Sistemas Complejos (IFISC), UIB-CSIC, UIB Campus, Palma de Mallorca E-07122, Spain.
ORCID-Profile: Mirko Goldmann, Irene Estébanez, Claudio R Mirasso, Ingo Fischer, Apostolos Argyris, Miguel C Soriano
Förderung
- Ministerio de Ciencia e Innovación
- H2020 Marie Skłodowska-Curie Actions
- HORIZON EUROPE Marie Sklodowska-Curie Actions
Zitieren
APA
Goldmann, M., Estébanez, I., Mirasso, C. R., Fischer, I., Argyris, A., & Soriano, M. C. (2025). Speedup of an all-optical delay-based reservoir computer via input rate increase and bandwidth enhancement. Chaos: An Interdisciplinary Journal of Nonlinear Science, 35(7). https://doi.org/10.1063/5.0273485
Vancouver
Goldmann M, Estébanez I, Mirasso CR, Fischer I, Argyris A, Soriano MC. Speedup of an all-optical delay-based reservoir computer via input rate increase and bandwidth enhancement. Chaos: An Interdisciplinary Journal of Nonlinear Science. 2025;35(7). doi:10.1063/5.0273485
BibTeX
@article{Goldmann2025,
author = {Goldmann, Mirko and Estébanez, Irene and Mirasso, Claudio R and Fischer, Ingo and Argyris, Apostolos and Soriano, Miguel C},
title = {Speedup of an all-optical delay-based reservoir computer via input rate increase and bandwidth enhancement},
journal = {Chaos: An Interdisciplinary Journal of Nonlinear Science},
year = {2025},
volume = {35},
number = {7},
doi = {10.1063/5.0273485}
}
EUVIMED