RNN Decoding of Linear Block Codes
This addresses the challenge of practical decoding for algebraic codes, offering incremental improvements in efficiency and performance for communication systems.
The paper tackles the problem of designing a low-complexity, near-optimal decoder for linear block codes by introducing a recurrent neural network (RNN) architecture, achieving comparable bit error rates to feed-forward neural networks with fewer parameters and improving performance over belief propagation on sparser Tanner graphs.
Designing a practical, low complexity, close to optimal, channel decoder for powerful algebraic codes with short to moderate block length is an open research problem. Recently it has been shown that a feed-forward neural network architecture can improve on standard belief propagation decoding, despite the large example space. In this paper we introduce a recurrent neural network architecture for decoding linear block codes. Our method shows comparable bit error rate results compared to the feed-forward neural network with significantly less parameters. We also demonstrate improved performance over belief propagation on sparser Tanner graph representations of the codes. Furthermore, we demonstrate that the RNN decoder can be used to improve the performance or alternatively reduce the computational complexity of the mRRD algorithm for low complexity, close to optimal, decoding of short BCH codes.