Optimal Training Channel Statistics for Neural-based Decoders
Optimal Training Channel Statistics for Neural-based Decoders
复制标题
基于神经的解码器的最佳训练通道统计
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
P. Piantanida
中科院分区：
文献类型：
--
作者：
Meryem Benammar;P. Piantanida
本文研究了基于深度学习的端到端信道编码设计。重点研究了基于神经网络的信道解码器的设计。我们证明了交叉熵损失的最优训练统计量的存在，该统计量允许网络在执行接近其最优决策规则的同时，将训练期间未见的信道统计量推广到信道统计量。数值结果说明了在二进制输入无记忆信道上的极值编码的应用。
This work investigates the design of End-to-End channel coding based on deep learning. The focus is on the design of neural networks based channel decoders. We demonstrate the existence of an optimal training statistic for the cross-entropy loss which allows the network to generalize to channel statistics unseen during training while performing close to their optimal decision rule. Numerical results illustrate an application to Polar coding on binary input memoryless channels.