MIST: A Novel Training Strategy for Low-latency Scalable Neural Net Decoders

TL;DR

This paper introduces MIST, a training strategy for CNN-based neural decoders that achieve high speed and robustness for convolutional and LDPC codes, outperforming existing methods especially in channel outage scenarios.

Contribution

The paper presents MIST, a novel training method enabling CNN decoders to match or surpass RNN decoders in performance while significantly increasing decoding speed and robustness.

Findings

Decoders achieve performance comparable to state-of-the-art neural decoders.

Decoding speed is more than 8 times faster than previous neural decoders.

Decoders outperform traditional methods in channel outage conditions.

Abstract

In this paper, we propose a low latency, robust and scalable neural net based decoder for convolutional and low-density parity-check (LPDC) coding schemes. The proposed decoders are demonstrated to have bit error rate (BER) and block error rate (BLER) performances at par with the state-of-the-art neural net based decoders while achieving more than 8 times higher decoding speed. The enhanced decoding speed is due to the use of convolutional neural network (CNN) as opposed to recurrent neural network (RNN) used in the best known neural net based decoders. This contradicts existing doctrine that only RNN based decoders can provide a performance close to the optimal ones. The key ingredient to our approach is a novel Mixed-SNR Independent Samples based Training (MIST), which allows for training of CNN with only 1\% of possible datawords, even for block length as high as 1000. The proposed decoder is robust as, once trained, the same decoder can be used for a wide range of SNR values. Finally, in the presence of channel outages, the proposed decoders outperform the best known decoders, {\it viz.} unquantized Viterbi decoder for convolutional code, and belief propagation for LDPC. This gives the CNN decoder a significant advantage in 5G millimeter wave systems, where channel outages are prevalent.