“…More recently, some progress has been made by applying Machine Learning (ML) techniques, where channel decoding is regarded as a classi ication task, and the encoder and decoder, implemented as Deep Neural Network (DNN) architectures, are jointly trained in a data-driven fashion [15,16,17,18,19,20,21]. In this context, the encoder/decoder pair forms an over-complete autoencoder, where the encoder DNN adds redundancy to the latent representation of the message to cope with the channel noise, and the decoder DNN extracts features from the noisy received signal for ef icient classi ication.…”