Optimization of recurrent neural network-based pre-distorter for coherent optical transmitter via stochastic orthogonal decomposition

Moshe Tzur; Gil Paryanti; Dan Sadot

Optimization of recurrent neural network-based pre-distorter for coherent optical transmitter via stochastic orthogonal decomposition

Moshe Tzur, Gil Paryanti, Dan Sadot

Department of Electrical & Computer Engineering

Ben-Gurion University of the Negev

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

A gradual training paradigm for Recurrent Neural Network-based pre-distorter is proposed. Stochastic decomposition is used to separate nonlinearity and quantization noise features. Performance improvement of more than 6dB is presented.

Original language	American English
Title of host publication	Signal Processing in Photonic Communications, SPPCom 2020
Publisher	Optica Publishing Group (formerly OSA)
ISBN (Print)	9781943580798
State	Published - 1 Jan 2020
Event	Signal Processing in Photonic Communications, SPPCom 2020 - Washington, United States Duration: 13 Jul 2020 → 16 Jul 2020

Publication series

Name	Optics InfoBase Conference Papers
Volume	Part F191-SPPCom 2020

Conference

Conference	Signal Processing in Photonic Communications, SPPCom 2020
Country/Territory	United States
City	Washington
Period	13/07/20 → 16/07/20

All Science Journal Classification (ASJC) codes

Electronic, Optical and Magnetic Materials
Mechanics of Materials

Cite this

@inproceedings{bd4f7f853bae464da3dd0793ae876449,

title = "Optimization of recurrent neural network-based pre-distorter for coherent optical transmitter via stochastic orthogonal decomposition",

abstract = "A gradual training paradigm for Recurrent Neural Network-based pre-distorter is proposed. Stochastic decomposition is used to separate nonlinearity and quantization noise features. Performance improvement of more than 6dB is presented.",

author = "Moshe Tzur and Gil Paryanti and Dan Sadot",

note = "Publisher Copyright: {\textcopyright} 2020 OSA - The Optical Society. All rights reserved.; Signal Processing in Photonic Communications, SPPCom 2020 ; Conference date: 13-07-2020 Through 16-07-2020",

year = "2020",

month = jan,

day = "1",

language = "American English",

isbn = "9781943580798",

series = "Optics InfoBase Conference Papers",

publisher = "Optica Publishing Group (formerly OSA)",

booktitle = "Signal Processing in Photonic Communications, SPPCom 2020",

}

Tzur, M, Paryanti, G & Sadot, D 2020, Optimization of recurrent neural network-based pre-distorter for coherent optical transmitter via stochastic orthogonal decomposition. in Signal Processing in Photonic Communications, SPPCom 2020. Optics InfoBase Conference Papers, vol. Part F191-SPPCom 2020, Optica Publishing Group (formerly OSA), Signal Processing in Photonic Communications, SPPCom 2020, Washington, United States, 13/07/20.

Optimization of recurrent neural network-based pre-distorter for coherent optical transmitter via stochastic orthogonal decomposition. / Tzur, Moshe; Paryanti, Gil; Sadot, Dan.
Signal Processing in Photonic Communications, SPPCom 2020. Optica Publishing Group (formerly OSA), 2020. (Optics InfoBase Conference Papers; Vol. Part F191-SPPCom 2020).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Optimization of recurrent neural network-based pre-distorter for coherent optical transmitter via stochastic orthogonal decomposition

AU - Tzur, Moshe

AU - Paryanti, Gil

AU - Sadot, Dan

PY - 2020/1/1

Y1 - 2020/1/1

N2 - A gradual training paradigm for Recurrent Neural Network-based pre-distorter is proposed. Stochastic decomposition is used to separate nonlinearity and quantization noise features. Performance improvement of more than 6dB is presented.

AB - A gradual training paradigm for Recurrent Neural Network-based pre-distorter is proposed. Stochastic decomposition is used to separate nonlinearity and quantization noise features. Performance improvement of more than 6dB is presented.

UR - http://www.scopus.com/inward/record.url?scp=85095576793&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781943580798

T3 - Optics InfoBase Conference Papers

BT - Signal Processing in Photonic Communications, SPPCom 2020

PB - Optica Publishing Group (formerly OSA)

T2 - Signal Processing in Photonic Communications, SPPCom 2020

Y2 - 13 July 2020 through 16 July 2020

ER -

Optimization of recurrent neural network-based pre-distorter for coherent optical transmitter via stochastic orthogonal decomposition

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Other files and links

Cite this