Deep Learning of Geometric Constellation Shaping including Fiber Nonlinearities

05/10/2018

∙

by   Rasmus T. Jones, et al.

∙

0

∙

share

A new geometric shaping method is proposed, leveraging unsupervised machine learning to optimize the constellation design. The learned constellation mitigates nonlinear effects with gains up to 0.13 bit/4D when trained with a simplified fiber channel model.