Reservoir-computing and neural-network-based equalization for short reach communication

Francesco Da Ros; Stenio Magalhães Ranzini; Yevhenii Osadchuk; Ali Cem; Bernard Jonathan Giron Castro; Darko Zibar

doi:10.1364/SPPCOM.2022.SpTu1J.1

Reservoir-computing and neural-network-based equalization for short reach communication

Francesco Da Ros, Stenio Magalhães Ranzini, Yevhenii Osadchuk, Ali Cem, Bernard Jonathan Giron Castro, Darko Zibar

Research output: Contribution to conference › Conference abstract for conference › Research › peer-review

131 Downloads (Pure)

Abstract

We review the use of neural-network-based equalizers for mitigating the power fading effect in intensity-modulated directly detected links, and compare the different approaches
reported in the literature.

Original language	English
Publication date	2022
Number of pages	2
DOIs	https://doi.org/10.1364/SPPCOM.2022.SpTu1J.1
Publication status	Published - 2022
Event	Signal Processing in Photonic Communications 2022 - Maastricht, Netherlands Duration: 24 Jul 2022 → 28 Jul 2022

Conference

Conference	Signal Processing in Photonic Communications 2022
Country/Territory	Netherlands
City	Maastricht
Period	24/07/2022 → 28/07/2022

Bibliographical note

From the session: Machine Learning in Optical Communications (SpTu1J)

Access to Document

10.1364/SPPCOM.2022.SpTu1J.1

FulltextAccepted author manuscript, 333 KB

OpenUrl availability

Full text

Cite this

@conference{a08450fa98a640d4b7f8cea6ea09fa87,

title = "Reservoir-computing and neural-network-based equalization for short reach communication",

abstract = "We review the use of neural-network-based equalizers for mitigating the power fading effect in intensity-modulated directly detected links, and compare the different approachesreported in the literature.",

author = "{Da Ros}, Francesco and Ranzini, {Stenio Magalh{\~a}es} and Yevhenii Osadchuk and Ali Cem and {Giron Castro}, {Bernard Jonathan} and Darko Zibar",

note = "From the session: Machine Learning in Optical Communications (SpTu1J); Signal Processing in Photonic Communications 2022 ; Conference date: 24-07-2022 Through 28-07-2022",

year = "2022",

doi = "10.1364/SPPCOM.2022.SpTu1J.1",

language = "English",

}

Reservoir-computing and neural-network-based equalization for short reach communication. / Da Ros, Francesco; Ranzini, Stenio Magalhães; Osadchuk, Yevhenii et al.
2022. Abstract from Signal Processing in Photonic Communications 2022, Maastricht, Netherlands.

Research output: Contribution to conference › Conference abstract for conference › Research › peer-review

TY - ABST

T1 - Reservoir-computing and neural-network-based equalization for short reach communication

AU - Da Ros, Francesco

AU - Ranzini, Stenio Magalhães

AU - Osadchuk, Yevhenii

AU - Cem, Ali

AU - Giron Castro, Bernard Jonathan

AU - Zibar, Darko

N1 - From the session: Machine Learning in Optical Communications (SpTu1J)

PY - 2022

Y1 - 2022

N2 - We review the use of neural-network-based equalizers for mitigating the power fading effect in intensity-modulated directly detected links, and compare the different approachesreported in the literature.

AB - We review the use of neural-network-based equalizers for mitigating the power fading effect in intensity-modulated directly detected links, and compare the different approachesreported in the literature.

U2 - 10.1364/SPPCOM.2022.SpTu1J.1

DO - 10.1364/SPPCOM.2022.SpTu1J.1

M3 - Conference abstract for conference

T2 - Signal Processing in Photonic Communications 2022

Y2 - 24 July 2022 through 28 July 2022

ER -

Reservoir-computing and neural-network-based equalization for short reach communication

Abstract

Conference

Bibliographical note

Access to Document

OpenUrl availability

Fingerprint

Cite this