Applying Neural Networks in Optical Communication Systems: Possible Pitfalls

Abstract

We investigate the risk of overestimating the performance gain when applying neural network based receivers in systems with pseudo random bit sequences or with limited memory depths, resulting in repeated short patterns. We show that with such sequences, a large artificial gain can be obtained which comes from pattern prediction rather than predicting or compensating the studied channel/phenomena.

References in corpus (2)

• Neural Machine Translation by Jointly Learning to Align and Translate
• Sequence to Sequence Learning with Neural Networks

Cited by in corpus (13)

• End-to-end Deep Learning of Optical Fiber Communications
• Compensation of Fiber Nonlinearities in Digital Coherent Systems Leveraging Long Short-Term Memory Neural Networks
• End-to-End Optimized Transmission over Dispersive Intensity-Modulated Channels Using Bidirectional Recurrent Neural Networks
• Artificial Neural Networks for Photonic Applications: From Algorithms to Implementation
• PAM-4 Transmission at 1550nm using Photonic Reservoir Computing Post-processing
• AdaNN: Adaptive Neural Network-based Equalizer via Online Semi-supervised Learning
• A Survey on Machine Learning for Optical Communication [Machine Learning View]
• Deep Learning for Communication over Dispersive Nonlinear Channels: Performance and Comparison with Classical Digital Signal Processing
• An Interpretable Mapping from a Communication System to a Neural Network for Optimal Transceiver-Joint Equalization
• Geometric Constellation Shaping for Fiber Optic Communication Systems via End-to-end Learning
• Performance versus Complexity Study of Neural Network Equalizers in Coherent Optical Systems
• Fiber-induced nonlinearity compensation in coherent optical systems by affinity propagation soft-clustering
• Transfer Learning for Neural Networks-based Equalizers in Coherent Optical Systems