论文信息 - Deep Learning Based Digital Back Propagation with Polarization State Rotation & Phase Noise Invariance

Deep Learning Based Digital Back Propagation with Polarization State Rotation & Phase Noise Invariance

A new deep learning training method for digital back propagation (DBP) is introduced. It is invariant to polarization state rotation and phase noise. Applying the method one gains more than 1 dB over standard DBP.

Amirhossein Ghazisaeidi | Benedikt Baeuerle | Marco Eppenberger | Bertold Ian Bitachon | Juerg Leuthold

[1] Zach DeVito,et al. Opt , 2017 .

[2] Guigang Zhang,et al. Deep Learning , 2016, Int. J. Semantic Comput..

[3] Tülay Adali,et al. Fully Complex Multi-Layer Perceptron Network for Nonlinear Signal Processing , 2002, J. VLSI Signal Process..

[4] Tülay Adali,et al. Complex-Valued Signal Processing: The Proper Way to Deal With Impropriety , 2011, IEEE Transactions on Signal Processing.

[5] Seb J Savory,et al. Digital filters for coherent optical receivers. , 2008, Optics express.