Experimental Evaluation of Computational Complexity for Different Neural Network Equalizers in Optical Communications
Pedro J. Freire, Yevhenii Osadchuk, Antonio Napoli, Bernhard Spinnler, Wolfgang Schairer, Nelson Costa, Jaroslaw E. Prilepsky, Sergei K. Turitsyn
arXiv:2109.08711v11 citations
Originality Synthesis-oriented
AI Analysis
This work provides incremental insights for optical communications researchers by benchmarking neural network equalizers.
The paper quantified the performance-complexity trade-off for neural network-based optical channel equalizers by comparing several architectures in TWC and SSMF setups.
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.