Details
| Original language | English |
|---|---|
| Pages (from-to) | 5097-5105 |
| Number of pages | 9 |
| Journal | ACS PHOTONICS |
| Volume | 12 |
| Issue number | 9 |
| Early online date | 11 Jul 2025 |
| Publication status | Published - 17 Sept 2025 |
Abstract
Reservoir computing (RC) is a powerful computational framework that addresses the need for efficient, low-power, and high-speed processing of time-dependent data. While RC has demonstrated strong signal processing and pattern recognition capabilities, its practical deployment in physical hardware is hindered by a critical challenge: the lack of efficient, scalable parameter optimization methods for real-world implementations. Traditionally, RC optimization has relied on software-based modeling, which limits the adaptability and efficiency of hardware-based systems, particularly in high-speed and energy-efficient computing applications. Herein, an in situ optimization approach was employed to demonstrate an optoelectronic delay-based RC system with digital delayed feedback, enabling direct, real-time tuning of system parameters without reliance on external computational resources. By simultaneously optimizing five parameters, normalized mean squared error (NMSE) values of 0.028, 0.561, and 0.271 are achieved in three benchmark tasks: waveform classification, time series prediction, and speech recognition, outperforming simulation-based optimization with NMSEs 0.054, 0.543, and 0.329, respectively, in two of the three tasks. This method enhances the feasibility of physical reservoir computing by bridging the gap between theoretical models and practical hardware implementation.
Keywords
- in situ optimization, neuromorphic computing, optoelectronic oscillator, physical computing, reservoir computing
ASJC Scopus subject areas
- Materials Science(all)
- Electronic, Optical and Magnetic Materials
- Biochemistry, Genetics and Molecular Biology(all)
- Biotechnology
- Physics and Astronomy(all)
- Atomic and Molecular Physics, and Optics
- Engineering(all)
- Electrical and Electronic Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: ACS PHOTONICS, Vol. 12, No. 9, 17.09.2025, p. 5097-5105.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - In-Situ Optimization of an Optoelectronic Reservoir Computer with Digital Delayed Feedback
AU - Morozko, Fyodor
AU - Watad, Shadad
AU - Naser, Amir
AU - Calà Lesina, Antonio
AU - Novitsky, Andrey
AU - Karabchevsky, Alina
N1 - Publisher Copyright: © 2025 The Authors. Published by American Chemical Society.
PY - 2025/9/17
Y1 - 2025/9/17
N2 - Reservoir computing (RC) is a powerful computational framework that addresses the need for efficient, low-power, and high-speed processing of time-dependent data. While RC has demonstrated strong signal processing and pattern recognition capabilities, its practical deployment in physical hardware is hindered by a critical challenge: the lack of efficient, scalable parameter optimization methods for real-world implementations. Traditionally, RC optimization has relied on software-based modeling, which limits the adaptability and efficiency of hardware-based systems, particularly in high-speed and energy-efficient computing applications. Herein, an in situ optimization approach was employed to demonstrate an optoelectronic delay-based RC system with digital delayed feedback, enabling direct, real-time tuning of system parameters without reliance on external computational resources. By simultaneously optimizing five parameters, normalized mean squared error (NMSE) values of 0.028, 0.561, and 0.271 are achieved in three benchmark tasks: waveform classification, time series prediction, and speech recognition, outperforming simulation-based optimization with NMSEs 0.054, 0.543, and 0.329, respectively, in two of the three tasks. This method enhances the feasibility of physical reservoir computing by bridging the gap between theoretical models and practical hardware implementation.
AB - Reservoir computing (RC) is a powerful computational framework that addresses the need for efficient, low-power, and high-speed processing of time-dependent data. While RC has demonstrated strong signal processing and pattern recognition capabilities, its practical deployment in physical hardware is hindered by a critical challenge: the lack of efficient, scalable parameter optimization methods for real-world implementations. Traditionally, RC optimization has relied on software-based modeling, which limits the adaptability and efficiency of hardware-based systems, particularly in high-speed and energy-efficient computing applications. Herein, an in situ optimization approach was employed to demonstrate an optoelectronic delay-based RC system with digital delayed feedback, enabling direct, real-time tuning of system parameters without reliance on external computational resources. By simultaneously optimizing five parameters, normalized mean squared error (NMSE) values of 0.028, 0.561, and 0.271 are achieved in three benchmark tasks: waveform classification, time series prediction, and speech recognition, outperforming simulation-based optimization with NMSEs 0.054, 0.543, and 0.329, respectively, in two of the three tasks. This method enhances the feasibility of physical reservoir computing by bridging the gap between theoretical models and practical hardware implementation.
KW - in situ optimization
KW - neuromorphic computing
KW - optoelectronic oscillator
KW - physical computing
KW - reservoir computing
UR - http://www.scopus.com/inward/record.url?scp=105010297751&partnerID=8YFLogxK
U2 - 10.1021/acsphotonics.5c01056
DO - 10.1021/acsphotonics.5c01056
M3 - Article
AN - SCOPUS:105010297751
VL - 12
SP - 5097
EP - 5105
JO - ACS PHOTONICS
JF - ACS PHOTONICS
SN - 2330-4022
IS - 9
ER -