Optical Fiber Communication Systems Based on End-to-End Deep Learning

Boris Karanov; Mathieu Chagnon; Vahid Aref; Domanic Lavery; Polina Bayvel; Laurent Schmalen

Optical Fiber Communication Systems Based on End-to-End Deep Learning

Signal Processing 2020-05-19 v1 Information Theory Machine Learning math.IT

Authors: Boris Karanov , Mathieu Chagnon , Vahid Aref , Domanic Lavery , Polina Bayvel , Laurent Schmalen

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.

Keywords

deep learning for wireless communications neural networks for signal processing deep learning for image reconstruction

Cite

@article{arxiv.2005.08785,
  title  = {Optical Fiber Communication Systems Based on End-to-End Deep Learning},
  author = {Boris Karanov and Mathieu Chagnon and Vahid Aref and Domanic Lavery and Polina Bayvel and Laurent Schmalen},
  journal= {arXiv preprint arXiv:2005.08785},
  year   = {2020}
}

Comments

Invited paper at IEEE Photonics Conference (IPC), Special Symposium for Machine Learning in Photonic Systems (SS MLPS)

Optical Fiber Communication Systems Based on End-to-End Deep Learning

Abstract

Keywords

Cite

Comments

Related papers