XClose

Institute of Communications and Connected Systems

Menu

End-to-End Learning in Optical Fiber Communications: Experimental Demonstration and Future Trends

ECOC 2020 | Karanov B, Oliari V, Chagnon M, Liga G, Alvarado A, et al. | Fiber-optic auto-encoders are demonstrated on an intensity modulation/direct detection testbed, outperforming state-of-the-a...

4 February 2021

End-to-End Learning in Optical Fiber Communications: Experimental Demonstration and Future Trends

Abstract

Fiber-optic auto-encoders are demonstrated on an intensity modulation/direct detection testbed, outperforming state-of-the-art signal processing. Algorithms for end-to-end optimization using experimentally collected data are discussed. The end-to-end learning framework is extended for performing optimization of the symbol distribution in probabilistically-shaped coherent systems.

Publication Type:Conference
Authors:Karanov B, Oliari V, Chagnon M, Liga G, Alvarado A, Aref V, Lavery D, Bayvel P, Schmalen L
Publisher:IEEE
Publication date:04/02/2021
Published Proceedings:2020 European Conference on Optical Communications, ECOC 2020
ISBN-13:9781728173610
Status:Published 
Name of Conference:2020 European Conference on Optical Communications, ECOC 2020
Conference start date:06/12/2020
Conference end date:10/12/2020
Conference location:Brussels, Belgium (Virtual)
Publisher URL:https://ieeexplore.ieee.org/document/9333265
DOI:http://dx.doi.org/10.1109/ECOC48923.2020.9333265
Full Text URL:

https://discovery.ucl.ac.uk/id/eprint/10125637/

Explore how UCL research is advancing the future technologies of a connected world: