Skip to Main content Skip to Navigation
Conference papers

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

Mathieu Leonardon 1, 2 Vincent Gripon 1, 2
2 Lab-STICC_2AI - Equipe Algorithm Architecture Interactions
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance : UMR6285
Abstract : 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.
Complete list of metadata
Contributor : Mathieu Léonardon Connect in order to contact the contributor
Submitted on : Monday, July 19, 2021 - 4:04:23 PM
Last modification on : Thursday, July 29, 2021 - 10:50:56 AM


Files produced by the author(s)


  • HAL Id : hal-03291030, version 1
  • ARXIV : 2105.04922


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. ⟨hal-03291030⟩



Record views


Files downloads