scholar.google.com › citations
Abstract: With increasingly higher data rate requirements imposed on short-reach links, coherent optical systems are expanding to shorter distances.
In this work, we make use of autoencoder-optimized geometric constellation shaping targeted at unamplified coherent systems. Recently, we experimentally ...
As the demand for higher data throughput in coherent optical communication systems increases, we need to find ways to increase capacity in existing and future ...
It is presented how an end-to-end machine learning algorithm can optimize the constellation geometry, and the importance of a well-suited model for the ...
Autoencoder-optimized geometric constellation shaping for unamplified coherent optical links. BM Oliveira, MS Neves, FP Guiomar, MCR Medeiros, PP Monteiro. CLEO ...
Oct 22, 2024 · In this work, we use an end-to-end deep learning framework to optimize the geometry of different constellation sizes, ranging from 8- to 128-ary ...
Geometric constellation shaping (GCS) has been proposed to enhance the performance of wavelength-division multiplexing (WDM) coherent optical fiber ...
Nov 7, 2022 · In this work, we use an end-to-end deep learning framework to optimize the geometry of different constellation sizes, ranging from 8- to 128-ary ...
Missing: ML- based
Such ML-aided models have enabled easier optimization and design (including inverse design) of optical systems. Keywords: Machine learning, photonics, neural ...
In this paper, we have investigated the performance of multidimen- sional geometric shaping based on lattices. Fast and low-complexity algorithms have been ...