• Technical Conference:  05 – 09 March 2023
  • Exhibition: 07 – 09 March 2023
  • San Diego Convention Center, San Diego, California, USA
Home > Poster

Poster

Domain Adaptation: the Key Enabler of Neural Network Equalizers in Coherent Optical Systems (Th2A.35)

Presenter: Pedro Jorge Freire de Carvalho Souza, Aston University

We introduce the domain adaptation and randomization approach for calibrating neural network-based equalizers for real transmissions, using synthetic data. The approach renders up to 99% training process reduction, which we demonstrate in three experimental setups.

Authors:Pedro Jorge Freire de Carvalho Souza, Aston University / Bernhard Spinnler, Infinera / Daniel Abode, Aston University / Jaroslaw E. Prilepsky, Aston University / Nelson Costa, Infinera / Abdallah Ali, Aston University / Wolfgang Schairer, Infinera / Antonio Napoli, Infinera / Andrew Ellis, Aston University / Sergei K. Turitsyn, Aston University


Poster Presentation

Authentication Required

Access to poster content is available to logged in registered attendees, please login now to participate.