Abstract
We show that separating the in-phase and quadrature component in optimized, machine-learning based demappers of optical communications systems with geometric constellation shaping reduces the required computational complexity whilst retaining their good performance.
© 2023 The Author(s)
PDF Article | Presentation VideoMore Like This
Andrej Rode and Laurent Schmalen
Mo3D.5 European Conference and Exhibition on Optical Communication (ECOC) 2022
Andrej Rode, Benedikt Geiger, and Laurent Schmalen
Th2A.32 Optical Fiber Communication Conference (OFC) 2022
Xun Guan, Amir Omidi, Ming Zeng, and Leslie Ann Rusch
SW4E.2 CLEO: Science and Innovations (CLEO:S&I) 2022