Abstract
Using end-to-end deep learning, we experimentally demonstrate the optimized design of geometric constellation shaping for coherent unamplified links. A power budget gain of more than 2 dB is demonstrated for 8-ary constellations.
© 2022 The Author(s)
PDF Article | Presentation VideoMore Like This
Beatriz M. Oliveira, Jorge H. Silva, Manuel S. Neves, Fernando P. Guiomar, Maria C. R. Medeiros, and Paulo P. Monteiro
Th3E.1 Optical Fiber Communication Conference (OFC) 2023
Ognjen Jovanovic, Metodi P. Yankov, Francesco Da Ros, and Darko Zibar
SF1F.2 CLEO: Science and Innovations (CLEO:S&I) 2023
Olga Vassilieva, Inwoong Kim, Hiroyuki Irie, Yohei Koganei, Hisao Nakashima, Yuichi Akiyama, Takeshi Hoshida, and Paparao Palacharla
Th1H.5 Optical Fiber Communication Conference (OFC) 2022