End-to-End Learning of Joint Geometric and Probabilistic Constellation Shaping
Vahid Aref, Mathieu Chagnon
Abstract
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).
Topics & Concepts
Decoding methodsProbabilistic logicConstellationMutual informationMetric (unit)Joint (building)Computer scienceAlgorithmArtificial intelligenceAutoencoderTheoretical computer scienceEngineeringDeep learningAstronomyArchitectural engineeringPhysicsOperations managementOptical Network TechnologiesWireless Signal Modulation Classificationgraph theory and CDMA systems