Decoding Short LDPC Codes via BP-RNN Diversity and Reliability-Based Post-Processing

Abstract

This paper investigates decoder diversity architectures for short low-density parity-check (LDPC) codes, based on recurrent neural network (RNN) models of the belief-propagation (BP) algorithm. We propose a new approach to achieve decoder diversity, by specializing BP-RNN decoders to specific classes of errors, with absorbing set support. We further combine our approach with an ordered statistics decoding (OSD) postprocessing step. We show that the OSD post-processing step effectively takes advantage of the bit-error rate optimization, deriving from the use of binary cross-entropy loss function, and the diversity brought by the use of multiple BP-RNN decoders, thus providing an efficient way to bridge the gap to maximum likelihood decoding.