Phase modulation of the input signal improves performance of reservoir computing

Ian Bauwens; Krishan Kumar Harkhoe; Peter Bienstman; Guy Verschaffelt; Guy Van Der Sande

doi:10.1109/IPC53466.2022.9975483

Phase modulation of the input signal improves performance of reservoir computing

Ian Bauwens, Krishan Kumar Harkhoe, Peter Bienstman, Guy Verschaffelt, Guy Van Der Sande

Research output: Unpublished contribution to conference › Poster

Abstract

In photonic reservoir computing, semiconductor lasers with delayed feedback have shown to be suited to efficiently solve difficult and time consuming
problems. The input data in this system is often optically injected into the reservoir Based on numerical simulations, we show that the performance depends heavily on the way that information is encoded in this optical injection signal. In our simulations we compare different input configurations
consisting of Mach Zehnder modulators and phase modulators for injecting the signal. We observe far better performance on a one step ahead time
series prediction task when modulating the phase of the injected signal rather than only modulating its amplitude.

Original language	English
DOIs	https://doi.org/10.1109/IPC53466.2022.9975483
Publication status	Published - 17 Nov 2022
Event	IEEE Photonics Conference 2022 - Hyatt Regency Vancouver, Vancouver, Canada Duration: 13 Nov 2022 → 17 Nov 2022 https://ieee-ipc.org/

Conference

Conference	IEEE Photonics Conference 2022
Country/Territory	Canada
City	Vancouver
Period	13/11/22 → 17/11/22
Internet address	https://ieee-ipc.org/

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Copyright:
Copyright 2023 Elsevier B.V., All rights reserved.

Access to Document

10.1109/IPC53466.2022.9975483

Cite this

@conference{811d5228b0214d4186d2f86c16ef002e,

title = "Phase modulation of the input signal improves performance of reservoir computing",

abstract = "In photonic reservoir computing, semiconductor lasers with delayed feedback have shown to be suited to efficiently solve difficult and time consumingproblems. The input data in this system is often optically injected into the reservoir Based on numerical simulations, we show that the performance depends heavily on the way that information is encoded in this optical injection signal. In our simulations we compare different input configurationsconsisting of Mach Zehnder modulators and phase modulators for injecting the signal. We observe far better performance on a one step ahead timeseries prediction task when modulating the phase of the injected signal rather than only modulating its amplitude.",

author = "Ian Bauwens and Harkhoe, {Krishan Kumar} and Peter Bienstman and Guy Verschaffelt and {Van Der Sande}, Guy",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE. Copyright: Copyright 2023 Elsevier B.V., All rights reserved.; IEEE Photonics Conference 2022 ; Conference date: 13-11-2022 Through 17-11-2022",

year = "2022",

month = nov,

day = "17",

doi = "10.1109/IPC53466.2022.9975483",

language = "English",

url = "https://ieee-ipc.org/",

}

TY - CONF

T1 - Phase modulation of the input signal improves performance of reservoir computing

AU - Bauwens, Ian

AU - Harkhoe, Krishan Kumar

AU - Bienstman, Peter

AU - Verschaffelt, Guy

AU - Van Der Sande, Guy

PY - 2022/11/17

Y1 - 2022/11/17

N2 - In photonic reservoir computing, semiconductor lasers with delayed feedback have shown to be suited to efficiently solve difficult and time consumingproblems. The input data in this system is often optically injected into the reservoir Based on numerical simulations, we show that the performance depends heavily on the way that information is encoded in this optical injection signal. In our simulations we compare different input configurationsconsisting of Mach Zehnder modulators and phase modulators for injecting the signal. We observe far better performance on a one step ahead timeseries prediction task when modulating the phase of the injected signal rather than only modulating its amplitude.

AB - In photonic reservoir computing, semiconductor lasers with delayed feedback have shown to be suited to efficiently solve difficult and time consumingproblems. The input data in this system is often optically injected into the reservoir Based on numerical simulations, we show that the performance depends heavily on the way that information is encoded in this optical injection signal. In our simulations we compare different input configurationsconsisting of Mach Zehnder modulators and phase modulators for injecting the signal. We observe far better performance on a one step ahead timeseries prediction task when modulating the phase of the injected signal rather than only modulating its amplitude.

UR - http://www.scopus.com/inward/record.url?scp=85145574116&partnerID=8YFLogxK

U2 - 10.1109/IPC53466.2022.9975483

DO - 10.1109/IPC53466.2022.9975483

M3 - Poster

T2 - IEEE Photonics Conference 2022

Y2 - 13 November 2022 through 17 November 2022

ER -

Phase modulation of the input signal improves performance of reservoir computing

Abstract

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

FWOAL960: High-speed low-power neuromorphic photonic information processing with chaotic cavities