Autoencoder-based end-to-end learning optimizes geometric constellation shapes and bit mappings, achieving up to 0.2 bits per QAM symbol GMI gain across data rates under transceiver impairments.
End-to-end Learning for GMI Optimized Geometric Constellation Shape
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
fields
cs.IT 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
End-to-end Learning for GMI Optimized Geometric Constellation Shape
Autoencoder-based end-to-end learning optimizes geometric constellation shapes and bit mappings, achieving up to 0.2 bits per QAM symbol GMI gain across data rates under transceiver impairments.