Skip to Main content Skip to Navigation
New interface
Conference papers

Efficient Deep Learning of Nonlinear Fiber-Optic Communications Using a Convolutional Recurrent Neural Network

Abtin Shahkarami 1, 2 Mansoor Yousefi 1, 2 Yves Jaouën 1, 2 
2 GTO - Télécommunications Optiques
LTCI - Laboratoire Traitement et Communication de l'Information
Abstract : Nonlinear channel impairments are a major obstacle in fiber-optic communication systems. To facilitate a higher data rate in these systems, the complexity of the underlying digital signal processing algorithms to compensate for these impairments must be reduced. Deep learning-based methods have proven successful in this area. However, the concept of computational complexity remains an open problem. In this paper, a lowcomplexity convolutional recurrent neural network (CNN+RNN) is considered for deep learning of the long-haul optical fiber communication systems where the channel is governed by the nonlinear Schrödinger equation. This approach reduces the computational complexity via balancing the computational load by capturing short-temporal distance features using strided convolution layers with ReLU activation, and the long-distance features using a many-to-one recurrent layer. We demonstrate that for a 16-QAM 100 G symbol/s system over 2000 km optical-link of 20 spans, the proposed approach achieves the bit-error-rate of the digital back-propagation (DBP) with substantially fewer floating-point operations (FLOPs) than the recently-proposed learned DBP, as well as the non-model-driven deep learningbased equalization methods using end-to-end MLP, CNN, RNN, and bi-RNN models. Index Terms-Fiber-optic communications, deep learning, nonlinear channel impairments, convolutional recurrent neural networks.
Complete list of metadata

https://hal.telecom-paris.fr/hal-03574305
Contributor : Abtin Shahkarami Connect in order to contact the contributor
Submitted on : Thursday, February 24, 2022 - 2:55:03 PM
Last modification on : Tuesday, November 8, 2022 - 11:53:08 AM
Long-term archiving on: : Wednesday, May 25, 2022 - 6:07:45 PM

File

ICMLA2021__Shahkarami_et_al__o...
Files produced by the author(s)

Identifiers

Collections

Citation

Abtin Shahkarami, Mansoor Yousefi, Yves Jaouën. Efficient Deep Learning of Nonlinear Fiber-Optic Communications Using a Convolutional Recurrent Neural Network. 20th IEEE International Conference on Machine Learning and Applications (ICMLA 2021), IEEE, Dec 2021, Pasadena, CA, United States. ⟨10.1109/icmla52953.2021.00112⟩. ⟨hal-03574305⟩

Share

Metrics

Record views

118

Files downloads

100