Conference paper Open Access

Experimental Verification of Complex-Valued Artificial Neural Network for Nonlinear Equalization in Coherent Optical Communication Systems

Pedro Jorge Freire; Vladislav Neskornuik; Antonio Napoli; Bernhard Spinnler; Nelson Costa; Jaroslaw E. Prilepsky; Emilio Riccardi; Sergei K. Turitsyn

We propose a novel design of neural networks for mitigating the fiber nonlinearity, employing a structure based on physical modeling. The neural network achieved nearly 5 times BER reduction in field trial when transmitting WDM 200G DP-16QAM over a 612 km legacy link.

All versions This version
Views 2929
Downloads 4040
Data volume 12.1 MB12.1 MB
Unique views 2626
Unique downloads 4040


Cite as