Neural Networks-Based Equalizers for Coherent Optical Transmission: Caveats and Pitfalls

This paper performs a detailed, multi-faceted analysis of key challenges and common design caveats related to the development of efficient neural networks (NN) based nonlinear channel equalizers in coherent optical communication systems. The goal of this study is to guide researchers and engineers working in this field. We start by clarifying the metrics used to evaluate the equalizers' performance, relating them to the loss functions employed in the training of the NN equalizers. The relationships between the channel propagation model's accuracy and the performance of the equalizers are addressed and quantified. Next, we assess the impact of the order of the pseudo-random bit sequence used to generate the - numerical and experimental - data as well as of the DAC memory limitations on the operation of the NN equalizers both during the training and validation phases. Finally, we examine the critical issues of overfitting limitations, the difference between using classification instead of regression, and batch-size-related peculiarities. We conclude by providing analytical expressions for the equalizers' complexity evaluation in the digital signal processing (DSP) terms and relate the metrics to the processing latency.

Automated summary

This paper provides a detailed and multi-faceted analysis of the challenges and design issues in the development of efficient neural network-based nonlinear channel equalizers in coherent optical communication systems. The study clarifies the evaluation metrics for equalizer performance, establishes the relationship between channel propagation model accuracy and equalizer performance, and examines the impact of pseudo-random bit sequence order and DAC memory limitations on equalizer operation. The paper also addresses overfitting limitations, classification versus regression, and batch-size-related peculiarities in NN equalizers.