Learning to decode linear codes using deep learning

Eliya Nachmani, Yair Be'Ery, David Burshtein

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

393 Scopus citations

Abstract

A novel deep learning method for improving the belief propagation algorithm is proposed. The method generalizes the standard belief propagation algorithm by assigning weights to the edges of the Tanner graph. These edges are then trained using deep learning techniques. A well-known property of the belief propagation algorithm is the independence of the performance on the transmitted codeword. A crucial property of our new method is that our decoder preserved this property. Furthermore, this property allows us to learn only a single codeword instead of exponential number of codewords. Improvements over the belief propagation algorithm are demonstrated for various high density parity check codes.

Original languageEnglish
Title of host publication54th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2016
PublisherInstitute of Electrical and Electronics Engineers
Pages341-346
Number of pages6
ISBN (Electronic)9781509045495
DOIs
StatePublished - 10 Feb 2017
Externally publishedYes
Event54th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2016 - Monticello, United States
Duration: 27 Sep 201630 Sep 2016

Publication series

Name54th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2016

Conference

Conference54th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2016
Country/TerritoryUnited States
CityMonticello
Period27/09/1630/09/16

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Computer Networks and Communications
  • Hardware and Architecture
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Learning to decode linear codes using deep learning'. Together they form a unique fingerprint.

Cite this