Error Structure Aware Parallel BP-RNN Decoders for Short LDPC Codes

Joachim Rosseel (1, 2) , Valérian Mannoni (1) , Valentin Savin (1) , Inbar Fijalkow (2)

1 CEA-LETI - Commissariat à l'énergie atomique et aux énergies alternatives - Laboratoire d'Electronique et de Technologie de l'Information
2 ETIS - UMR 8051 - Equipes Traitement de l'Information et Systèmes

This article deals with the decoding of short block length Low Density Parity Check (LDPC) codes. It has already been demonstrated that Belief Propagation (BP) can be adjusted to the short coding length, thanks to its modeling by a Recurrent Neural Network (BP-RNN). To strengthen this adaptation, we introduce a new training method for the BP-RNN. Its aim is to specialize the BP-RNN on error events sharing the same structural properties. This approach is then associated with a new decoder composed of several parallel specialized BP-RNN decoders, each trained on correcting a different type of error events. Our results show that the proposed specialized BP-RNNs working in parallel effectively enhance the decoding capacity for short block length LDPC codes.

Domaines: Traitement du signal et de l'image [eess.SP]

Joachim Rosseel, Valérian Mannoni, Valentin Savin, Inbar Fijalkow. Error Structure Aware Parallel BP-RNN Decoders for Short LDPC Codes. International Symposium on Topics in Coding (ISTC), Aug 2021, Montréal, Canada. ⟨10.1109/ISTC49272.2021.9594200⟩. ⟨hal-03438477⟩