Optical Equalization using Photonic Reservoir Computing with Optical Analog Signal Injection

Photonic reservoir computing with optical pre-processing enables equalization of the signal entirely in the optical domain. We compare the performance of reservoir computing-based estimation of 28GBd PAM-4 transmission over 100km SSMF with Kramers-Kronig DSP results.

[1]  M. Shtaif,et al.  Kramers-Kronig PAM transceiver , 2017, 2017 Optical Fiber Communications Conference and Exhibition (OFC).

[2]  Marco Ruffini,et al.  An Overview on Application of Machine Learning Techniques in Optical Networks , 2018, IEEE Communications Surveys & Tutorials.

[3]  Simon Ohlendorf,et al.  100 km 56 GBd PAM-4 Transmission using Photonic Reservoir Computing , 2019, 45th European Conference on Optical Communication (ECOC 2019).

[4]  Laurent Larger,et al.  Tutorial: Photonic Neural Networks in Delay Systems , 2018, Journal of Applied Physics.

[5]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[6]  R. Lang,et al.  External optical feedback effects on semiconductor injection laser properties , 1980 .

[7]  Ingo Fischer,et al.  Photonic machine learning implementation for signal recovery in optical communications , 2018, Scientific Reports.