Online Label Recovery for Deep Learning-based Communication through Error Correcting Codes
Online Label Recovery for Deep Learning-based Communication through Error Correcting Codes
复制标题
DOI：
10.1109/iswcs.2018.8491189
复制
发表时间：
2018-07
期刊：
影响因子：
--
通讯作者：
Stefan Schibisch;Sebastian Cammerer;Sebastian Dörner;J. Hoydis;S. Brink
中科院分区：
文献类型：
--
作者：
Stefan Schibisch;Sebastian Cammerer;Sebastian Dörner;J. Hoydis;S. Brink
我们证明，纠错码（ECC）可用于构建标记数据集，以微调“可训练”通信系统，而无需牺牲传输已知符号的资源。这使得自适应系统能够进行动态训练，以补偿信道条件的缓慢波动或不同的硬件损伤。我们研究了损坏的训练数据的影响，并表明基于正确标签的训练至关重要。所提出的方法可以应用于完全端到端训练的通信系统（自动编码器）以及仅具有一些可训练组件的系统。这通过使用可在运行时优化的可训练预均衡器神经网络 (NN) 扩展传统 OFDM 系统来举例说明。
We demonstrate that error correcting codes (ECCs) can be used to construct a labeled data set for finetuning of “trainable” communication systems without sacrificing resources for the transmission of known symbols. This enables adaptive systems, which can be trained on-the-fly to compensate for slow fluctuations in channel conditions or varying hardware impairments. We examine the influence of corrupted training data and show that it is crucial to train based on correct labels. The proposed method can be applied to fully end-to-end trained communication systems (autoencoders) as well as systems with only some trainable components. This is exemplified by extending a conventional OFDM system with a trainable pre-equalizer neural network (NN) that can be optimized at run time.