Learned Decimation for Neural Belief Propagation Decoders
Paper in proceeding, 2021

We introduce a two-stage decimation process to improve the performance of neural belief propagation (NBP), recently introduced by Nachmani et al., for short low-density parity-check (LDPC) codes. In the first stage, we build a list by iterating between a conventional NBP decoder and guessing the least reliable bit. The second stage iterates between a conventional NBP decoder and learned decimation, where we use a neural network to decide the decimation value for each bit. For a (128,64) LDPC code, the proposed NBP with decimation outperforms NBP decoding by 0.75dB and performs within 1dB from maximum-likelihood decoding at a block error rate of 10-4.

Author

Andreas Buchberger

Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks

Christian Häger

Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks

Henry D. Pfister

Duke University

Laurent Schmalen

Karlsruhe Institute of Technology (KIT)

Alexandre Graell I Amat

Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

15206149 (ISSN)

Vol. 2021-June 8273-8277

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Invited paper
Toronto, Canada,

Reliable and Secure Coded Edge Computing

Swedish Research Council (VR) (2020-03687), 2021-01-01 -- 2024-12-31.

Areas of Advance

Information and Communication Technology

Subject Categories

Telecommunications

Probability Theory and Statistics

Signal Processing

DOI

10.1109/ICASSP39728.2021.9414407

More information

Latest update

4/6/2022 5