End-to-End Learning of Joint Geometric and Probabilistic Constellation Shaping

12/09/2021

∙

We present a novel autoencoder-based learning of joint geometric and probabilistic constellation shaping for coded-modulation systems. It can maximize either the mutual information (for symbol-metric decoding) or the generalized mutual information (for bit-metric decoding).

READ FULL TEXT

End-to-End Learning of Joint Geometric and Probabilistic Constellation Shaping

Model-Based Deep Learning of Joint Probabilistic and Geometric Shaping for Optical Communication

Post-FEC BER Prediction for Bit-Interleaved Coded Modulation with Probabilistic Shaping

End-to-End Learning of Geometrical Shaping Maximizing Generalized Mutual Information

End-to-end Learning for GMI Optimized Geometric Constellation Shape

Joint Learning of Probabilistic and Geometric Shaping for Coded Modulation Systems

Geometric Constellation Shaping for Fiber-Optic Channels via End-to-End Learning

Decoding Methods for Neural Narrative Generation

End-to-End Learning of Joint Geometric and Probabilistic Constellation Shaping

Related Research

Model-Based Deep Learning of Joint Probabilistic and Geometric Shaping for Optical Communication

Post-FEC BER Prediction for Bit-Interleaved Coded Modulation with Probabilistic Shaping

End-to-End Learning of Geometrical Shaping Maximizing Generalized Mutual Information

End-to-end Learning for GMI Optimized Geometric Constellation Shape

Joint Learning of Probabilistic and Geometric Shaping for Coded Modulation Systems

Geometric Constellation Shaping for Fiber-Optic Channels via End-to-End Learning

Decoding Methods for Neural Narrative Generation