In-Situ Optimization of an Optoelectronic Reservoir Computer with Digital Delayed Feedback

Research output: Contribution to journalArticleResearchpeer review

Authors

External Research Organisations

  • Ben-Gurion University of the Negev
  • Belarusian State University
  • Lancaster University
View graph of relations

Details

Original languageEnglish
Pages (from-to)5097-5105
Number of pages9
JournalACS PHOTONICS
Volume12
Issue number9
Early online date11 Jul 2025
Publication statusPublished - 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

Cite this

In-Situ Optimization of an Optoelectronic Reservoir Computer with Digital Delayed Feedback. / Morozko, Fyodor; Watad, Shadad; Naser, Amir et al.
In: ACS PHOTONICS, Vol. 12, No. 9, 17.09.2025, p. 5097-5105.

Research output: Contribution to journalArticleResearchpeer review

Morozko F, Watad S, Naser A, Calà Lesina A, Novitsky A, Karabchevsky A. In-Situ Optimization of an Optoelectronic Reservoir Computer with Digital Delayed Feedback. ACS PHOTONICS. 2025 Sept 17;12(9):5097-5105. Epub 2025 Jul 11. doi: 10.1021/acsphotonics.5c01056
Morozko, Fyodor ; Watad, Shadad ; Naser, Amir et al. / In-Situ Optimization of an Optoelectronic Reservoir Computer with Digital Delayed Feedback. In: ACS PHOTONICS. 2025 ; Vol. 12, No. 9. pp. 5097-5105.
Download
@article{fdec045a4e2d48368635543ed7ba7897,
title = "In-Situ Optimization of an Optoelectronic Reservoir Computer with Digital Delayed Feedback",
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",
author = "Fyodor Morozko and Shadad Watad and Amir Naser and {Cal{\`a} Lesina}, Antonio and Andrey Novitsky and Alina Karabchevsky",
note = "Publisher Copyright: {\textcopyright} 2025 The Authors. Published by American Chemical Society.",
year = "2025",
month = sep,
day = "17",
doi = "10.1021/acsphotonics.5c01056",
language = "English",
volume = "12",
pages = "5097--5105",
journal = "ACS PHOTONICS",
issn = "2330-4022",
publisher = "American Chemical Society",
number = "9",

}

Download

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 -

By the same author(s)