CSI-aided Robust Neural-based Decoders

Meryem Benammar (1) , Eduardo Dadalto-Camara-Gomes (2) , Pablo Piantanida (2)

1 DEOS - Département Electronique, Optronique et Signal
2 L2S - Laboratoire des signaux et systèmes

In this work, we investigate the design of neural based channel decoders for the Binary Asymmetric Channel (BAC), which exhibits robustness issues related to training/testing channel parameters mismatch. Rather than enforcing the independence of the trained model to the channel parameter as in our previous work, we show that providing even a coarse (possibly imperfect) quantized CSI to the decoder, allows to build a single robust neural decoder for all values of channel parameters.

Mots clés: Neural based decoders; Channel State Information (CSI)

Domaines: Traitement du signal et de l'image [eess.SP]

Meryem Benammar, Eduardo Dadalto-Camara-Gomes, Pablo Piantanida. CSI-aided Robust Neural-based Decoders. 11th International Symposium on Topics in Coding, Aug 2021, Montréal, Canada. pp.0. ⟨hal-03522702⟩