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.
|Title of host publication||2020 European Conference on Optical Communications, ECOC 2020|
|Publisher||Institute of Electrical and Electronics Engineers|
|Publication status||Published - 4 Feb 2021|
|Event||46th European Conference on Optical Communications, ECOC 2020 - Virtual, Brussels, Belgium|
Duration: 6 Dec 2020 → 10 Dec 2020
|Conference||46th European Conference on Optical Communications, ECOC 2020|
|Abbreviated title||ECOC 2020|
|Period||6/12/20 → 10/12/20|
Bibliographical noteFunding Information:
The work received funding from the EU’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie project COIN (676448), UK EPSRC TRANSNET grant EP/R035342/1, and the Netherlands Organisation for Scientific Research (NWO) via the VIDI Grant ICONIC (15685). The work of G. Liga is funded by the EU-ROTECH postdoc programme under the European Union’s Horizon 2020 research and innovation programme (Marie Skłodowska-Curie grant agreement No 754462). The work of A. Alvarado received funding from the European Research Council (ERC) under the EU’s Horizon 2020 research and innovation programme (757791).
© 2020 IEEE.
Copyright 2021 Elsevier B.V., All rights reserved.