Learning to Denoise and Decode: A Novel Residual Neural Network Decoder for Polar Codes

Polar codes have been adopted as the control channel coding scheme in the fifth generation new radio (5G NR) standard due to its capacity-achievable property. Traditional polar decoding algorithms such as successive cancellation (SC) suffer from high latency problem because of their sequential decoding nature. Neural network decoder (NND) has been proved to be a candidate for polar decoder since it is capable of one-shot decoding and parallel computing. In his paper, we propose a residual neural network decoder (RNND) for polar codes. Different from previous works which directly use neural network for decoding symbols received from the channel, the proposed RNND introduces a denoising module based on residual learning before NND. The proposed residual learning denoiser is able to remove remarkable amount of noise from received signals. Numerical results show that on one hand our proposed RNND outperforms traditional NND with regard to the BER performance under comparable latency. On the other hand, although the proposed scheme is a little inferior to the traditional successive cancellation list decoder when the BER performance is under consideration, it reduces significant decoding latency with the aid of the parallel structure of neural network and modern graphical processing units.