CRISP: Curriculum based Sequential Neural Decoders for Polar Code Family

arXiv2210.00313MaRDI QIDQ6412584

Author name not available (Why is that?)

Publication date: 1 October 2022

Abstract: Polar codes are widely used state-of-the-art codes for reliable communication that have recently been included in the 5th generation wireless standards (5G). However, there remains room for the design of polar decoders that are both efficient and reliable in the short blocklength regime. Motivated by recent successes of data-driven channel decoders, we introduce a novel $extbfC$ur$extbfRI$culum based $extbfS$equential neural decoder for $extbfP$olar codes (CRISP). We design a principled curriculum, guided by information-theoretic insights, to train CRISP and show that it outperforms the successive-cancellation (SC) decoder and attains near-optimal reliability performance on the Polar(32,16) and Polar(64,22) codes. The choice of the proposed curriculum is critical in achieving the accuracy gains of CRISP, as we show by comparing against other curricula. More notably, CRISP can be readily extended to Polarization-Adjusted-Convolutional (PAC) codes, where existing SC decoders are significantly less reliable. To the best of our knowledge, CRISP constructs the first data-driven decoder for PAC codes and attains near-optimal performance on the PAC(32,16) code.

Has companion code repository: https://github.com/hebbarashwin/neural_polar_decoder

This page was built for publication: CRISP: Curriculum based Sequential Neural Decoders for Polar Code Family

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6412584)