A Complex-valued Neural Network for Fiber Nonlinearity Mitigation

A complex-valued triplet-input neural network for fiber nonlinearity compensation is proposed. Numerical results show 0.2 dB Q factor improvement and 25% computational complexity reduction, compared with the real-valued triplet-input neural network. © 2021 The Author(s)

[1]  Alex Alvarado,et al.  Revisiting Efficient Multi-Step Nonlinearity Compensation With Machine Learning: An Experimental Demonstration , 2020, Journal of Lightwave Technology.

[2]  Vijay Vusirikala,et al.  Field and lab experimental demonstration of nonlinear impairment compensation using neural networks , 2019, Nature Communications.

[3]  Vijay Vusirikala,et al.  Evolution from 8QAM live traffic to PS 64-QAM with Neural-Network Based Nonlinearity Compensation on 11000 km Open Subsea Cable , 2018, 2018 Optical Fiber Communications Conference and Exposition (OFC).

[4]  Amirhossein Ghazisaeidi,et al.  Submarine Transmission Systems Using Digital Nonlinear Compensation and Adaptive Rate Forward Error Correction , 2016, Journal of Lightwave Technology.

[5]  Yoshua Bengio,et al.  Unitary Evolution Recurrent Neural Networks , 2015, ICML.

[6]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[7]  R. Essiambre,et al.  Nonlinear Shannon Limit in Pseudolinear Coherent Systems , 2012, Journal of Lightwave Technology.

[8]  Akira Hirose,et al.  Generalization Characteristics of Complex-Valued Feedforward Neural Networks in Relation to Signal Coherence , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[9]  Arthur James Lowery,et al.  Improved single channel backpropagation for intra-channel fiber nonlinearity compensation in long-haul optical communication systems. , 2010, Optics express.

[10]  E. Ip,et al.  Nonlinear Compensation Using Backpropagation for Polarization-Multiplexed Transmission , 2010, Journal of Lightwave Technology.