activity
20172022
most citedApplying Neural Networks in Optical Communication Systems: Possible Pitfalls

185 citations · 186 across the 3 of their papers we have counts for

collaborators

8 papers

cs.IT20221 cited

Distributed Transmission and Spatially Coupled Forward Error Correction in Regenerative Multipoint-to-Point Networks

Laurent Schmalen, Tobias A. Eriksson, Fred Buchali +2

We investigate the performance of coded modulation for multi-hop regenerative optical networks. We analyze options for computing decoder input LLRs, show reach increases by optimiz…

quant-ph2019

Inter-Core Crosstalk Impact of Classical Channels on CV-QKD in Multicore Fiber Transmission

Tobias A. Eriksson, Benjamin J. Puttnam, Georg Rademacher +5

Crosstalk-induced excess noise is experimentally characterized for continuous-variable quantum key distribution, spatially multiplexed with WDM PM-16QAM channels in a 19-core fiber…

cs.IT2018

Geometric Constellation Shaping for Fiber Optic Communication Systems via End-to-end Learning

Rasmus T. Jones, Tobias A. Eriksson, Metodi P. Yankov +4

In this paper, an unsupervised machine learning method for geometric constellation shaping is investigated. By embedding a differentiable fiber channel model within two neural netw…

quant-ph2018

Coexistence of Continuous Variable Quantum Key Distribution and 7 12.5 Gbit/s Classical Channels

Tobias A. Eriksson, Takuya Hirano, Motoharu Ono +6

We study coexistence of CV-QKD and 7 classical 12.5 Gbit/s on-off keying channels in WDM transmission over the C-band. We demonstrate key generation with a distilled secret key rat…

cs.IT2018

Deep Learning of Geometric Constellation Shaping including Fiber Nonlinearities

Rasmus T. Jones, Tobias A. Eriksson, Metodi P. Yankov +1

A new geometric shaping method is proposed, leveraging unsupervised machine learning to optimize the constellation design. The learned constellation mitigates nonlinear effects wit…

cs.IT2018

End-to-end Deep Learning of Optical Fiber Communications

Boris Karanov, Mathieu Chagnon, Félix Thouin +5

In this paper, we implement an optical fiber communication system as an end-to-end deep neural network, including the complete chain of transmitter, channel model, and receiver. Th…