Using Deep Neural Networks to Predict and Improve the Performance of Polar Codes - Ecole Nationale d'Ingénieurs de Brest Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Using Deep Neural Networks to Predict and Improve the Performance of Polar Codes

Résumé

Polar codes can theoretically achieve very competitive Frame Error Rates. In practice, their performance may depend on the chosen decoding procedure, as well as other parameters of the communication system they are deployed upon. As a consequence, designing efficient polar codes for a specific context can quickly become challenging. In this paper, we introduce a methodology that consists in training deep neural networks to predict the frame error rate of polar codes based on their frozen bit construction sequence. We introduce an algorithm based on Projected Gradient Descent that leverages the gradient of the neural network function to generate promising frozen bit sequences. We showcase on generated datasets the ability of the proposed methodology to produce codes more efficient than those used to train the neural networks, even when the latter are selected among the most efficient ones.
Fichier principal
Vignette du fichier
Using_Deep_Neural_Networks_to_Predict_and_Improve_the_Performance_of_Polar_Codes.pdf (250.38 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03291030 , version 1 (19-07-2021)

Identifiants

Citer

Mathieu Leonardon, Vincent Gripon. Using Deep Neural Networks to Predict and Improve the Performance of Polar Codes. ISTC 2021: 11th IEEE International Symposium on Topics in Coding, Aug 2021, Montréal, Canada. ⟨10.1109/ISTC49272.2021.9594059⟩. ⟨hal-03291030⟩
48 Consultations
184 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More