Artificial neural networks for nonlinear pulse shaping in optical fibers


We use a supervised machine-learning model based on a neural network to predict the temporal and spectral intensity profiles of the pulses that form upon nonlinear propagation in optical fibers with both normal and anomalous second-order dispersion. We also show that the model is able to retrieve the parameters of the nonlinear propagation from the pulses observed at the output of the fiber. Various initial pulse shapes as well as initially chirped pulses are investigated.

Publication DOI:
Divisions: Engineering & Applied Sciences > Electrical, Electronic & Power Engineering
Additional Information: © 2020, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Uncontrolled Keywords: Pulse shaping, Neural networks, Nonlinear propagation, Optical fibers
Full Text Link: https://arxiv.o ... /2002.08815.pdf
Related URLs:
PURE Output Type: Article
Published Date: 2020-11
Published Online Date: 2020-07-03
Accepted Date: 2020-06-17
Authors: Boscolo, Sonia ( 0000-0001-5388-2893)
Finot, Christophe



Version: Accepted Version

Access Restriction: Restricted to Repository staff only until 3 July 2021.

License: Creative Commons Attribution Non-commercial No Derivatives

Export / Share Citation


Additional statistics for this record