Active Deep Decoding of Linear Codes
Active Deep Decoding of Linear Codes
复制标题
DOI：
10.1109/tcomm.2019.2955724
复制
发表时间：
2020-02-01
影响因子：
8.3
通讯作者：
Be'ery, Yair
中科院分区：
文献类型：
--
作者：
Be'ery, Ishay;Raviv, Nir;Be'ery, Yair
在深度学习中，高质量的数据对于训练稳健的模型至关重要。虽然在其他领域，数据稀疏且收集成本高昂，但在错误解码中，可以自由查询和标记，从而允许潜在的数据利用。利用这一事实并受到主动学习的启发，引入了两种新颖的方法来改进加权置信传播（WBP）解码。这些方法将机器学习概念与错误解码措施结合起来。对于 BCH(63,36)、(63,45) 和 (127,64) 码，采用循环减少的奇偶校验矩阵，与原始 WBP 相比，在瀑布区域提高了高达 0.4dB，在 FER 的错误本底区域提高了高达 1.5dB，这通过智能地采样数据来证明，而无需增加推理（解码）复杂性。所提出的方法通过将纠错领域的领域知识纳入深度学习模型来构成模型增强的示例指南。这些指南可以适用于任何其他基于深度学习的通信块。
High quality data is essential in deep learning to train a robust model. While in other fields data is sparse and costly to collect, in error decoding it is free to query and label thus allowing potential data exploitation. Utilizing this fact and inspired by active learning, two novel methods are introduced to improve Weighted Belief Propagation (WBP) decoding. These methods incorporate machine-learning concepts with error decoding measures. For BCH(63,36), (63,45) and (127,64) codes, with cycle-reduced parity-check matrices, improvement of up to 0.4dB at the waterfall region, and of up to 1.5dB at the error-floor region in FER, over the original WBP, is demonstrated by smartly sampling the data, without increasing inference (decoding) complexity. The proposed methods constitutes an example guidelines for model enhancement by incorporation of domain knowledge from error-correcting field into a deep learning model. These guidelines can be adapted to any other deep learning based communication block.