Achievable Information Rates for Nonlinear Fiber Communication via End-to-end Autoencoder Learning
Paper i proceeding, 2018
Machine learning is used to compute achievable information rates (AIRs) for a simplified fiber channel. The approach jointly optimizes the input distribution (constellation shaping) and the auxiliary channel distribution to compute AIRs without explicit channel knowledge in an end-to-end fashion.
Författare
Shen Li
Chalmers, Elektroteknik, Kommunikations- och antennsystem, Kommunikationssystem
Christian Häger
Duke University
Chalmers, Elektroteknik, Kommunikations- och antennsystem, Kommunikationssystem
Nil Garcia
Chalmers, Elektroteknik, Kommunikations- och antennsystem, Kommunikationssystem
Henk Wymeersch
Chalmers, Elektroteknik, Kommunikations- och antennsystem, Kommunikationssystem
2018 European Conference on Optical Communication (ECOC)
Vol. 2018-September 8535456
44th European Conference on Optical Communication, ECOC 2018
Rome, Italy,
Rome, Italy,
Coding for terabit-per-second fiber-optical communications (TERA)
Europeiska kommissionen (EU), 2017-01-01 -- 2019-12-31.
Ämneskategorier
Annan maskinteknik
Telekommunikation
Kommunikationssystem
DOI
10.1109/ECOC.2018.8535456