Paper ID | SS-8.2 | ||
Paper Title | LEARNED DECIMATION FOR NEURAL BELIEF PROPAGATION DECODERS | ||
Authors | Andreas Buchberger, Christian Häger, Chalmers University of Technology, Sweden; Henry D. Pfister, Duke University, United States; Laurent Schmalen, Karlsruhe Institute of Technology, Germany; Alexandre Graell i Amat, Chalmers University of Technology, Sweden | ||
Session | SS-8: Near-ML Decoding of Error-correcting Codes: Algorithms and Implementation | ||
Location | Gather.Town | ||
Session Time: | Wednesday, 09 June, 16:30 - 17:15 | ||
Presentation Time: | Wednesday, 09 June, 16:30 - 17:15 | ||
Presentation | Poster | ||
Topic | Special Sessions: Near-ML Decoding of Error-correcting Codes: Algorithms and Implementation | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | 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 0.75 dB and performs within 1 dB from maximum-likelihood decoding at a block error rate of 10^(-4). |