Deep Learning of Geometric Constellation Shaping including Fiber Nonlinearities
arXiv:1805.03785
Abstract
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.
3 pages, 6 figures, submitted to ECOC 2018