Low-complexity Recurrent Neural Network-based Polar Decoder with Weight Quantization Mechanism
This work addresses memory-intensive deployment issues for deep learning in communication systems, offering an incremental improvement for polar code decoding in 5G NR.
The paper tackled the problem of high memory and computational complexity in neural network-based polar decoders for communication systems by proposing a low-complexity RNN decoder with weight quantization, achieving a 98% reduction in memory overhead with slight performance loss.
Polar codes have drawn much attention and been adopted in 5G New Radio (NR) due to their capacity-achieving performance. Recently, as the emerging deep learning (DL) technique has breakthrough achievements in many fields, neural network decoder was proposed to obtain faster convergence and better performance than belief propagation (BP) decoding. However, neural networks are memory-intensive and hinder the deployment of DL in communication systems. In this work, a low-complexity recurrent neural network (RNN) polar decoder with codebook-based weight quantization is proposed. Our test results show that we can effectively reduce the memory overhead by 98% and alleviate computational complexity with slight performance loss.