A neural-network LLR demapper and a CNN autoencoder transceiver achieve BER/SER comparable to conventional QAM receivers over AWGN, with performance strongly dependent on training SNR.
Deepreceiver: A deep learning-based intelligent receiver for wireless communications in the physical layer,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Neural Network-based Information-Theoretic Transceivers for High-Order Modulation Schemes
A neural-network LLR demapper and a CNN autoencoder transceiver achieve BER/SER comparable to conventional QAM receivers over AWGN, with performance strongly dependent on training SNR.