光通信中不同神经网络均衡器计算复杂度的实验评估
信号处理
2021-09-21 v1 机器学习
摘要
针对基于神经网络的光信道均衡器，我们通过比较分析若干神经网络架构，量化了其性能与复杂度之间的权衡，并给出了在 TWC 和 SSMF 装置下的结果。
引用
@article{arxiv.2109.08711,
title = {Experimental Evaluation of Computational Complexity for Different Neural Network Equalizers in Optical Communications},
author = {Pedro J. Freire and Yevhenii Osadchuk and Antonio Napoli and Bernhard Spinnler and Wolfgang Schairer and Nelson Costa and Jaroslaw E. Prilepsky and Sergei K. Turitsyn},
journal= {arXiv preprint arXiv:2109.08711},
year = {2021}
}
备注
ORAL presentation at the Asia Communications and Photonics Conference (ACP 2021)