Neural Network Training for OSNR Estimation -- From Prototype to Product
Signal Processing
2020-03-06 v1
Abstract
A method for in-service OSNR measurement with a coherent transceiver is presented and experimentally verified. A neural network is employed to identify and remove the nonlinear noise contribution to the estimated OSNR.
Keywords
Cite
@article{arxiv.2003.02333,
title = {Neural Network Training for OSNR Estimation -- From Prototype to Product},
author = {Andrew D. Shiner and Mohammad E. Mousa-Pasandi and Meng Qiu and Michael A. Reimer and Eui Young Park and Michael Hubbard and Qunbi Zhuge and Francisco J. Vaquero Caballero and Maurice O'Sullivan},
journal= {arXiv preprint arXiv:2003.02333},
year = {2020}
}
Comments
This invited talk summary was prepared for proceedings of the symposium on 'The Role of Machine Learning for the Next-generation of Optical Communication Systems and Networks' at the Optical Fiber and Communication Conference (OFC) in March 2020