arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.04221cs.ITcs.SYeess.SYmath.IT
收藏

用于LDPC MinSum解码的神经网络优化度特定权重

Neural-Network-Optimized Degree-Specific Weights for LDPC MinSum Decoding

Linfang Wang, Sean Chen, Jonathan Nguyen, Divsalar Dariush, Richard Wesel

摘要:

神经归一化最小和(N-NMS)解码通过在每次迭代中向每个校验到变量消息分配动态乘法权重,在线性分组码上提供比常规归一化最小和(NMS)更好的帧出错率(FER)性能。以前的N-NMS工作主要研究短长度分组码(N < 1000),因为要训练的N-NMS参数的数量与奇偶检验矩阵中的边的数量和迭代次数成比例,这在使用Pytorch或Tensorflow进行训练时强加了不切实际的内存要求。本文提供了有效的方法来训练参数的N-NMS,支持N-NMS的更长的块长度。具体来说,本文介绍了一个家庭的神经2维归一化(N-2D-NMS)解码器与各种减少的参数集,并显示性能如何变化的参数集选择。N-2D-NMS解码器共享关于校验节点和/或可变节点度的权重。仿真结果证明了这种方法的有效性,表明N-NMS的训练权重与校验节点度、变量节点度和迭代次数有很强的相关性。对基于(3096,1032)原型图的raptor-like(PBRL)码的进一步仿真结果表明,N-2D-NMS解码器可以实现与N-NMS相同的误码率,而所需的参数显著减少。用于(16200,7200)DVBS-2标准LDPC码的N-2D-NMS解码器显示出比置信传播更低的错误平层。最后,本文提出了一种前馈结构与递归结构相结合的混合译码结构。该混合结构显示出与全前馈结构相似的解码性能,但需要显著更少的参数。

英文摘要:

Neural Normalized MinSum (N-NMS) decoding delivers better frame error rate (FER) performance on linear block codes than conventional normalized MinSum (NMS) by assigning dynamic multiplicative weights to each check-to-variable message in each iteration. Previous N-NMS efforts have primarily investigated short-length block codes (N < 1000), because the number of N-NMS parameters to be trained is proportional to the number of edges in the parity check matrix and the number of iterations, which imposes am impractical memory requirement when Pytorch or Tensorflow is used for training. This paper provides efficient approaches to training parameters of N-NMS that support N-NMS for longer block lengths. Specifically, this paper introduces a family of neural 2-dimensional normalized (N-2D-NMS) decoders with with various reduced parameter sets and shows how performance varies with the parameter set selected. The N-2D-NMS decoders share weights with respect to check node and/or variable node degree. Simulation results justify this approach, showing that the trained weights of N-NMS have a strong correlation to the check node degree, variable node degree, and iteration number. Further simulation results on the (3096,1032) protograph-based raptor-like (PBRL) code show that N-2D-NMS decoder can achieve the same FER as N-NMS with significantly fewer parameters required. The N-2D-NMS decoder for a (16200,7200) DVBS-2 standard LDPC code shows a lower error floor than belief propagation. Finally, a hybrid decoding structure combining a feedforward structure with a recurrent structure is proposed in this paper. The hybrid structure shows similar decoding performance to full feedforward structure, but requires significantly fewer parameters.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑