Achievable Information Rates for Nonlinear Fiber Communication via End-to-end Autoencoder Learning
Paper in 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.

Author

Shen Li

Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks

Christian Häger

Duke University

Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks

Nil Garcia

Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks

Henk Wymeersch

Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks

Published in

European Conference on Optical Communication, ECOC

Vol. 2018-September art. no 8535456
978-153864862-9 (ISBN)

Conference

44th European Conference on Optical Communication, ECOC 2018
Rome, Italy, 2018-09-22 - 2018-09-26

Research Project(s)

Coding for terabit-per-second fiber-optical communications (TERA)

European Commission (EC) (EC/H2020/749798), 2017-01-01 -- 2019-12-31.

Categorizing

Subject Categories (SSIF 2011)

Other Mechanical Engineering

Telecommunications

Communication Systems

Identifiers

DOI

10.1109/ECOC.2018.8535456

More information

Latest update

3/21/2023