论文标题
基于ADMM的二进制线性代码的解码器有助于深度学习
ADMM-based Decoder for Binary Linear Codes Aided by Deep Learning
论文作者
论文摘要
受深度学习进展的启发（DL），这项工作提出了深层神经网络的辅助解码算法，用于二进制线性代码。基于深度展开的概念，我们通过展开乘数的交替方向方法（ADMM）二元解码器来设计解码网络。此外，我们提出了两种改进的版本的拟议网络。第一个将惩罚参数转换为一组迭代依赖性参数，第二个是基于具有可调斜率的分段线性函数的特殊设计的惩罚函数。数值结果表明，所得的DL ADED解码器的表现优于具有相似计算复杂性的各种低密度均衡检查（LDPC）代码的原始ADMM-含量解码器。
Inspired by the recent advances in deep learning (DL), this work presents a deep neural network aided decoding algorithm for binary linear codes. Based on the concept of deep unfolding, we design a decoding network by unfolding the alternating direction method of multipliers (ADMM)-penalized decoder. In addition, we propose two improved versions of the proposed network. The first one transforms the penalty parameter into a set of iteration-dependent ones, and the second one adopts a specially designed penalty function, which is based on a piecewise linear function with adjustable slopes. Numerical results show that the resulting DL-aided decoders outperform the original ADMM-penalized decoder for various low density parity check (LDPC) codes with similar computational complexity.
