XClose

Institute of Communications and Connected Systems

Home
Menu

Optical Fiber Communication Systems Based on End-to-End Deep Learning: (Invited Paper)

2020 IEEE Photonics Conference (IPC) | Karanov B, Chagnon M, Aref V, Lavery D, Bayvel P, et al. | We investigate end-to-end optimized optical transmission systems based on feedforward or bidirecti...

16 November 2020

Optical Fiber Communication Systems Based on End-to-End Deep Learning: (Invited Paper)

Abstract

 

We investigate end-to-end optimized optical transmission systems based on feedforward or bidirectional recurrent neural networks (BRNN) and deep learning. In particular, we report the first experimental demonstration of a BRNN auto-encoder, highlighting the performance improvement achieved with recurrent processing for communication over dispersive nonlinear channels.

Publication Type:Conference
Authors:Karanov B, Chagnon M, Aref V, Lavery D, Bayvel P, Schmalen L
Publisher:2020 IEEE Photonics Conference (IPC)
Publication date:16/11/2020
Published proceedings:2020 IEEE Photonics Conference, IPC 2020 - Proceedings
Name of Conference:2020 IEEE Photonics Conference 
Conference start date:28/09/2020
Conference end date:01/10/2020
Conference location:Vancouver, BC, Canada
ISBN -13:9781728158914
Status:Published 
DOI:http://dx.doi.org/10.1109/IPC47351.2020.9252544
Full Text URL:https://discovery.ucl.ac.uk/id/eprint/10120662/

Explore how UCL research is advancing the future technologies of a connected world: