Deep Learning-Based Decoding of Block Markov Superposition Transmission
Sheng Bi, Qianfan Wang, Zengzhe Chen, Jiachen Sun, Xiao Ma · 2019
In this paper, we present deep learning-based decoding of block Markov superposition transmission (BMST). For the basic code, a deep neural network (DNN) is trained, providing with good decoding performance. The complexity of the trained DNN can be reduced by removing those negligibly small coefficients. For the BMST code, we introduce a sliding window decoding algorithm, which integrates the DNN decoder of the basic code in an iterative manner. Numerical results show that the performance of our proposed scheme is close to that of the BMST system with conventional decoders and matches well with the corresponding lower bound of BMST. The above results verify that the extra gain and lower bound of BMST are effective for neural network decoder and thus demonstrate the universality of BMST.