Learning to Decode Linear Block Codes using Adaptive Gradient-Descent Bit-Flipping

Jovan Milojkovic, Srdan Brkic, Predrag Ivanis, Bane Vasic

Research output: Chapter in Book/Report/Conference proceedingConference contribution


In this paper we propose a generalization of the recently published adaptive diversity gradient-descent bit flipping (AD-GDBF) decoder, named generalized AD-GDBF (gAD-GDBF) decoder. While the original AD-GDBF decoder was designed for the binary symmetric channel and used mostly to decode regular low-density parity-check codes, the gAD-GDBF algorithm incorporates several improvements which makes it eligible for the additive white Gaussian channel and decoding of arbitrary linear block code. The gAD-GDBF decoder uses the genetic algorithm to optimize a set of learnable parameters, for a targeted linear block code. The effectiveness of the proposed method is verified on short Bose-Chaudhuri-Hocquenghem (BCH) codes, where it was shown that for the same number of decoding iterations the gAD-GDBF decoder outperforms the belief-propagation decoder in terms of bit error rate and at the same time reduces the decoding complexity significantly.

Original languageEnglish (US)
Title of host publication2023 12th International Symposium on Topics in Coding, ISTC 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350326116
StatePublished - 2023
Event12th International Symposium on Topics in Coding, ISTC 2023 - Brest, France
Duration: Sep 4 2023Sep 8 2023

Publication series

Name2023 12th International Symposium on Topics in Coding, ISTC 2023


Conference12th International Symposium on Topics in Coding, ISTC 2023


  • Bose-Chaudhuri-Hocquenghem codes
  • bit-flipping
  • diversity decoding
  • genetic algorithm
  • gradient-descent
  • linear block codes

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Safety, Risk, Reliability and Quality

Cite this