BROWSE
Detail
Journal Article
Learning strategies for neural min-sum decoding of LDPC codes
- Authors
- Hyeyeon Na, Hosung Park, Hee-Youl Kwak, Seok-Ki Ahn
- Issue Date
- 2025-02
- Citation
- ICT Express, v.11, no.1, pp.161-166
- ISSN
- 2405-9595
- Publisher
- 한국통신학회
- Language
- Korean
- Type
- Journal Article
- Abstract
- The min-sum (MS) decoding for low-density parity-check codes, though less complex than the sum–product algorithm, suffers from worse error-correcting performance. For enhancement, neural MS decoders leveraging deep learning have recently been introduced, but how to train them has not been sufficiently discussed. In this paper, we propose a novel dataset construction method and also propose systematic learning strategies by finding a good combination of dataset composition, loss functions, weight sharing, weight assignment, and weight update method. Simulations demonstrate that the proposed method achieves better error-correcting performance than other works, especially in the error floor region, within a limited number of iterations.
- KSP Keywords
- Construction Method, Dataset construction, Error floor, Error-correcting, LDPC Codes, Learning strategies, Low Density Parity Check(LDPC), Min-sum decoding, Novel dataset, Parity check codes, Weight assignment
This work is distributed under the term of Creative Commons License (CCL)
(CC BY NC ND)
(CC BY NC ND)
