Domain Adaptation: the Key Enabler of Neural Network Equalizers in Coherent Optical Systems

02/25/2022

∙

by   Pedro J. Freire, et al.

∙

0

∙

share

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.