Turbo Autoencoder: Deep learning based channel code for point-to-point communication channels
TurboAutoencoder:Deeplearningbasedchannelcodeforpoint-to-pointcommunicationchannelsAbstract1.介绍2.问题形成3.TruboAE:结构设计和训练3.1TurboAE的设计3.2基于直通估计器的TurboAE二值化设计3.3神经可训练性设计4.实验结果4.1TurboAE的块长编码增益4.2非AWGN信道上的