A complex-valued neural network for fiber nonlinearity mitigation

Pinjing He; Aiying Yang; Peng Guo; Yaojun Qiao; Xiangjun Xin

A complex-valued neural network for fiber nonlinearity mitigation

Pinjing He
, Aiying Yang^*
, Peng Guo
, Yaojun Qiao
, Xiangjun Xin

^*Corresponding author for this work

School of Optics and Photonics

Beijing Institute of Technology
Beijing University of Posts and Telecommunications

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

Abstract

A complex-valued triplet-input neural network for fiber nonlinearity compensation is proposed. Numerical results show 0.2 dB Q factor improvement and 25% computational complexity reduction, compared with the real-valued triplet-input neural network.

Original language	English
Article number	JS2B.3
Journal	Optics InfoBase Conference Papers
Publication status	Published - 2021
Event	26th Optoelectronics and Communications Conference, OECC 2021 - Virtual, Online, China Duration: 3 Jul 2021 → 7 Jul 2021

Cite this

@article{d1189f01df094fda96c0d06861820bb3,

title = "A complex-valued neural network for fiber nonlinearity mitigation",

abstract = "A complex-valued triplet-input neural network for fiber nonlinearity compensation is proposed. Numerical results show 0.2 dB Q factor improvement and 25\% computational complexity reduction, compared with the real-valued triplet-input neural network.",

author = "Pinjing He and Aiying Yang and Peng Guo and Yaojun Qiao and Xiangjun Xin",

note = "Publisher Copyright: {\textcopyright} OSA 2021, {\textcopyright} 2021 The Author(s); 26th Optoelectronics and Communications Conference, OECC 2021 ; Conference date: 03-07-2021 Through 07-07-2021",

year = "2021",

language = "English",

journal = "Optics InfoBase Conference Papers",

issn = "2162-2701",

}

TY - JOUR

T1 - A complex-valued neural network for fiber nonlinearity mitigation

AU - He, Pinjing

AU - Yang, Aiying

AU - Guo, Peng

AU - Qiao, Yaojun

AU - Xin, Xiangjun

PY - 2021

Y1 - 2021

N2 - A complex-valued triplet-input neural network for fiber nonlinearity compensation is proposed. Numerical results show 0.2 dB Q factor improvement and 25% computational complexity reduction, compared with the real-valued triplet-input neural network.

AB - A complex-valued triplet-input neural network for fiber nonlinearity compensation is proposed. Numerical results show 0.2 dB Q factor improvement and 25% computational complexity reduction, compared with the real-valued triplet-input neural network.

UR - https://www.scopus.com/pages/publications/85119606562

M3 - Conference article

AN - SCOPUS:85119606562

SN - 2162-2701

JO - Optics InfoBase Conference Papers

JF - Optics InfoBase Conference Papers

M1 - JS2B.3

T2 - 26th Optoelectronics and Communications Conference, OECC 2021

Y2 - 3 July 2021 through 7 July 2021

ER -

A complex-valued neural network for fiber nonlinearity mitigation

Abstract

Other files and links

Fingerprint

Cite this