End-to-end Learning for GMI Optimized Geometric Constellation Shape
Autoencoder-based geometric shaping is proposed that includes optimizing bit mappings. Up to 0.2 bits/QAM symbol gain in GMI is achieved for a variety of data rates and in the presence of transceiver impairments. The gains can be harvested with standard binary FEC at no cost w.r.t. conventional BICM.
Code (1)
Similar Papers 제목 키워드 기반
Experimental Validation of Sequence-Wise Predistorter for Evaluation of Geometrically Shaped 128-QAM
A predistorter for transmitter nonlinearities is applied to the evaluation of a geometrically shaped constellation, such that constellation points are transmitted correctly during the evaluation of the geometrically shap…
Geometric Constellation Shaping for Fiber Optic Communication Systems via End-to-end Learning
In this paper, an unsupervised machine learning method for geometric constellation shaping is investigated. By embedding a differentiable fiber channel model within two neural networks, the learning algorithm is optimizi…
BIG-bench Machine LearningGeometric Constellation Shaping with Low-complexity Demappers for Wiener Phase-noise Channels
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 compl…
Geometric Constellation Shaping for Phase-noise Channels Using a Differentiable Blind Phase Search
We perform geometric constellation shaping with optimized bit labeling using a binary autoencoder including a differential blind phase search (BPS). Our approach enables full end-to-end training of optical coherent trans…
Joint Learning of Geometric and Probabilistic Constellation Shaping
The choice of constellations largely affects the performance of communication systems. When designing constellations, both the locations and probability of occurrence of the points can be optimized. These approaches are …