Experimental Evaluation of Computational Complexity for Different Neural Network Equalizers in Optical Communications
arXiv:2109.08711
Abstract
Addressing the neural network-based optical channel equalizers, we quantify the trade-off between their performance and complexity by carrying out the comparative analysis of several neural network architectures, presenting the results for TWC and SSMF set-ups.
ORAL presentation at the Asia Communications and Photonics Conference (ACP 2021)