In this work, we propose a neural adjusted min-sum (NAMS) decoder for low-density parity-check (LDPC) codes. In particular, we improve the traditional normalized min-sum (NMS) decoder by introducing a selection mechanism to adjust the check-node update step, where either the min-sum rule or the belief propagation (BP) rule is selected. Besides, we unfold the modified decoder into a model-driven neural network, where layer-dependent trainable parameters are introduced as weights in the Tanner graph and optimized by gradient descent-based methods during network training. Simulation results demonstrate that the proposed NAMS decoder is able to provide superior error-correction performance as compared to the neural NMS decoder, with only slightly increased computational complexity. Moreover, in certain circumstances, the proposed NAMS decoder even outperforms the neural BP decoder, with much lower computational complexity.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Neural Adjusted Min-Sum Decoding for LDPC Codes


    Contributors:
    Yu, Haochen (author) / Zhao, Ming-Min (author) / Lei, Ming (author) / Zhao, Min-Jian (author)


    Publication date :

    2023-10-10


    Size :

    1083121 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Low-Latency Decoding of EG LDPC Codes

    Zhang, J. / Yedidia, J. S. / Fossorier, M. | British Library Online Contents | 2007


    Noise-Assisted List Decoding for 5G LDPC Codes

    Gao, Jian / Wang, Hao / Tian, Kuangda | IEEE | 2022



    Dynamic Dual Quantization-Domain Decoding for NR LDPC Codes

    Kim, Taehyun / Park, JooSung | IEEE | 2021


    CRC-Aided Adaptive Belief Propagation Decoding of NR LDPC Codes

    Zhang, Xianwen / Jiang, Ming / Zhu, Mingyang et al. | IEEE | 2022