Low Complexity Convolutional neural networks for equalization in optical fiber transmission

Mohannad Abu-Romoh; Nelson Costa; Antonio Napoli; Jõao Pedro; Yves Jaoüen; Mansoor Yousefi

Low Complexity Convolutional neural networks for equalization in optical fiber transmission

Mohannad Abu-Romoh
, Nelson Costa
, Antonio Napoli
, Jõao Pedro
, Yves Jaoüen
, Mansoor Yousefi

Research output: Contribution to journal › Conference article › peer-review

Abstract

A convolutional neural network is proposed to mitigate fiber transmission effects, achieving a five-fold reduction in trainable parameters compared to alternative equalizers, and 3.5 dB improvement in MSE compared to DBP with comparable complexity. 1.

Original language	English
Article number	SpM5C.5
Journal	Optics InfoBase Conference Papers
Publication status	Published - 1 Jan 2021
Event	Signal Processing in Photonic Communications, SPPCom 2021 - Part of OSA Advanced Photonics Congress 2021 - Virtual, Online, United States Duration: 26 Jul 2021 → 29 Jul 2021

Cite this

@article{e701b3533b7841938f74a3ce1ea22015,

title = "Low Complexity Convolutional neural networks for equalization in optical fiber transmission",

abstract = "A convolutional neural network is proposed to mitigate fiber transmission effects, achieving a five-fold reduction in trainable parameters compared to alternative equalizers, and 3.5 dB improvement in MSE compared to DBP with comparable complexity. 1.",

author = "Mohannad Abu-Romoh and Nelson Costa and Antonio Napoli and J{\~o}ao Pedro and Yves Jao{\"u}en and Mansoor Yousefi",

note = "Publisher Copyright: {\textcopyright} 2021 The Author(s).; Signal Processing in Photonic Communications, SPPCom 2021 - Part of OSA Advanced Photonics Congress 2021 ; Conference date: 26-07-2021 Through 29-07-2021",

year = "2021",

month = jan,

day = "1",

language = "English",

journal = "Optics InfoBase Conference Papers",

issn = "2162-2701",

}

TY - JOUR

T1 - Low Complexity Convolutional neural networks for equalization in optical fiber transmission

AU - Abu-Romoh, Mohannad

AU - Costa, Nelson

AU - Napoli, Antonio

AU - Pedro, Jõao

AU - Jaoüen, Yves

AU - Yousefi, Mansoor

PY - 2021/1/1

Y1 - 2021/1/1

N2 - A convolutional neural network is proposed to mitigate fiber transmission effects, achieving a five-fold reduction in trainable parameters compared to alternative equalizers, and 3.5 dB improvement in MSE compared to DBP with comparable complexity. 1.

AB - A convolutional neural network is proposed to mitigate fiber transmission effects, achieving a five-fold reduction in trainable parameters compared to alternative equalizers, and 3.5 dB improvement in MSE compared to DBP with comparable complexity. 1.

M3 - Conference article

AN - SCOPUS:85120562447

SN - 2162-2701

JO - Optics InfoBase Conference Papers

JF - Optics InfoBase Conference Papers

M1 - SpM5C.5

T2 - Signal Processing in Photonic Communications, SPPCom 2021 - Part of OSA Advanced Photonics Congress 2021

Y2 - 26 July 2021 through 29 July 2021

ER -

Low Complexity Convolutional neural networks for equalization in optical fiber transmission

Abstract

Fingerprint

Cite this