Iterative Decoding Algorithms Powered by Deep Learning

In this paper, we analyze the performance of neural belief propagation (BP) decoding on the additive white Gaussian noise (AWGN) channel, compared to the traditional BP algorithm. Previous investigations have shown that assigning pre-trained weights to BP messages can significantly improve the decod...

Full description

Saved in:
Bibliographic Details
Published in:2025 12th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN) pp. 1 - 6
Main Authors: Jovanovic, Dimitrije, Ivanis, Predrag
Format: Conference Proceeding
Language:English
Published: IEEE 09.06.2025
Subjects:
AWGN channel
AWGN channels
Belief propagation
Bit error rate
Codes
Decoding
Deep learning
Iterative decoding
MDPC codes
neural network
Neural networks
TensorFlow
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract In this paper, we analyze the performance of neural belief propagation (BP) decoding on the additive white Gaussian noise (AWGN) channel, compared to the traditional BP algorithm. Previous investigations have shown that assigning pre-trained weights to BP messages can significantly improve the decoding performance in case of high-density parity-check (HDPC) codes, by reducing the negative impact of short cycles. These weights are trained by a neural network whose structure matches the trellis of the decoder. Specifically, we show that medium-density paritycheck (MDPC) codes decoded with neural BP algorithm can achieve lower bit error rate versus HDPC codes with the same codeword length and the same code rate.
AbstractList In this paper, we analyze the performance of neural belief propagation (BP) decoding on the additive white Gaussian noise (AWGN) channel, compared to the traditional BP algorithm. Previous investigations have shown that assigning pre-trained weights to BP messages can significantly improve the decoding performance in case of high-density parity-check (HDPC) codes, by reducing the negative impact of short cycles. These weights are trained by a neural network whose structure matches the trellis of the decoder. Specifically, we show that medium-density paritycheck (MDPC) codes decoded with neural BP algorithm can achieve lower bit error rate versus HDPC codes with the same codeword length and the same code rate.
Author Jovanovic, Dimitrije
Ivanis, Predrag
Author_xml – sequence: 1
  givenname: Dimitrije
  orcidid: 0009-0001-5842-9139
  surname: Jovanovic
  fullname: Jovanovic, Dimitrije
  email: jd235018p@student.etf.bg.ac.rs
  organization: School of Electrical Engineering, University of Belgrade,Belgrade,Serbia
– sequence: 2
  givenname: Predrag
  orcidid: 0000-0003-4565-1141
  surname: Ivanis
  fullname: Ivanis, Predrag
  email: predrag.ivanis@etf.rs
  organization: School of Electrical Engineering, University of Belgrade,Belgrade,Serbia
BookMark eNo1j1FLwzAUhSPog879Ax-K7525N03S-1jm1EJRkb6PNL2Zga0dWVH27y2oTwfOd_jg3IjLYRxYiHuQKwBJD7XftB_VqzGlLlYoUc81QIGWLsSSLJVKgS61tvJamHri5Kb4xdkj-7GPwy6r9rsxxenzcMrex29O3GfdecZ8zBp2aZg3t-IquP2Jl3-5EO3Tpl2_5M3bc72umjySmnLqkF3hS4tMHkAZQwXJDlRANBbRokMXKJTG6176XpECLJzTPUCwLqiFuPvVRmbeHlM8uHTe_r9RP5S8RGU
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/IcETRAN66854.2025.11114279
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798331585570
EndPage 6
ExternalDocumentID 11114279
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i93t-9b2ea4c872e9c113669490b13f22672272a2af9f86c5d0cd393124aa5d11f7af3
IEDL.DBID RIE
IngestDate Wed Aug 27 07:41:15 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i93t-9b2ea4c872e9c113669490b13f22672272a2af9f86c5d0cd393124aa5d11f7af3
ORCID 0000-0003-4565-1141
0009-0001-5842-9139
PageCount 6
ParticipantIDs ieee_primary_11114279
PublicationCentury 2000
PublicationDate 2025-June-9
PublicationDateYYYYMMDD 2025-06-09
PublicationDate_xml – month: 06
  year: 2025
  text: 2025-June-9
  day: 09
PublicationDecade 2020
PublicationTitle 2025 12th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN)
PublicationTitleAbbrev ICETRAN
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.9113674
Snippet In this paper, we analyze the performance of neural belief propagation (BP) decoding on the additive white Gaussian noise (AWGN) channel, compared to the...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms AWGN channel
AWGN channels
Belief propagation
Bit error rate
Codes
Decoding
Deep learning
Iterative decoding
MDPC codes
neural network
Neural networks
TensorFlow
Training
Title Iterative Decoding Algorithms Powered by Deep Learning
URI https://ieeexplore.ieee.org/document/11114279
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NSwMxEA22ePCkYkWtSg5et80m2c3OsWiLBSlFivRWssmkFrQt_RD89ybpVvHgwVtICGESMpN5mTdDyB0AWkDjnRxWuESik4kuvDLMClSGS-tsxHRfntRgUIzHMKzI6pELg4gx-AxboRn_8u3CbANU1g7XW3IFNVJTKt-RtapEoimDdt90R8-dQZ4XES3hWWs_4VfplGg5esf_XPOENH44eHT4bV1OyQHOz0jej0mQvYaiD95vDCO08zZdeA__9X1Nh6HkGVpafvphXNIqeeq0QUa97uj-MakqHyQzEJsESo5amkJxBBOKruQggZWpcP6xpDhXXHPtwBW5ySwzVoDwZlrrzKapU9qJc1KfL-Z4QSimjFkQwIw0suQCMs2yUgS3LwAZ7pI0gsyT5S63xWQv7tUf_U1yFHY2BkvBNalvVlu8IYfmYzNbr27jiXwB5J2MUg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aBT2pWPHtHrxum02yjzkWbWmxLkUW6a1kk0ktaFv6EPz3JumqePDgLSSEMAmZyXyZb4aQWwDUgMo6OTQzoUAjQplZZRhnmComtNEe033up3meDYcwqMjqnguDiD74DBuu6f_y9UytHVTWdNdbsBS2yU4sBKMbulaVSjSi0OypdvHUypMk83gJixtfU34VT_G2o3Pwz1UPSf2HhRcMvu3LEdnC6TFJej4NstVRwb31HN1I0Hodz6yP__K2DAau6BnqoPywwzgPqvSp4zopOu3irhtWtQ_CCfBVCCVDKVSWMgTlyq4kIICWETf2uZQyljLJpAGTJSrWVGkO3BpqKWMdRSaVhp-Q2nQ2xVMSYESpBg5UCSVKxiGWNC65c_wclGHOSN3JPJpvsluMvsQ9_6P_hux1i8f-qN_LHy7IvttlHzoFl6S2Wqzxiuyq99Vkubj2p_MJZaOPmQ
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2025+12th+International+Conference+on+Electrical%2C+Electronic+and+Computing+Engineering+%28IcETRAN%29&rft.atitle=Iterative+Decoding+Algorithms+Powered+by+Deep+Learning&rft.au=Jovanovic%2C+Dimitrije&rft.au=Ivanis%2C+Predrag&rft.date=2025-06-09&rft.pub=IEEE&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1109%2FIcETRAN66854.2025.11114279&rft.externalDocID=11114279