University of Hertfordshire

From the same journal

By the same authors

  • Ivan Aldaya
  • Elias Giacoumidis
  • Athanasios Tsokanos
  • Mutsam Jarajreh
  • Yannuo Wen
  • Jinlong Wei
  • Gabriel Campuzano
  • Marcelo L.F. Abbade
  • Liam P. Barry
View graph of relations
Original languageEnglish
Pages (from-to)5820-5823
Number of pages4
JournalOptics Letters
Publication statusPublished - 15 Oct 2020


A novel nonlinear equalizer based on a multiple-input multiple-output (MIMO) deep neural network (DNN) is proposed and experimentally demonstrated for compensation of inter-subcarrier nonlinearities in a 40 Gb/s coherent optical orthogonal frequency division multiplexing system. Experimental results reveal that MIMO-DNN can extend the power margin by 4 dB at 2000 km of standard single-mode fiber transmission when compared to linear compensation or conventional single-input single-output DNN. It is also found that MIMO-DNN outperforms digital back propagation by increasing up to 1 dB the effective Q-factor and reducing by a factor of three the computational cost.


Funding Information: Funding. Fundação de Amparo à Pesquisa do Estado de São Paulo (2018/25339-4); Science Foundation Ireland (12/RC/2276, 13/RC/2077, 15/US-C2C/I3132); Conselho Nacional de Desenvolvimento Científico e Tecnológico (311035/2018-3, 432303/2018-9). Publisher Copyright: © 2020 Optical Society of America.

ID: 28001397