Deep Learning for Decoding of Linear Codes - A Syndrome-Based Approach
This work addresses decoding challenges in communication systems, offering a robust method that avoids overfitting, though it is incremental in applying existing neural network designs to a specific domain.
The authors tackled the problem of soft decoding linear codes at arbitrary block lengths using deep neural networks, achieving performance that sometimes approaches the ordered statistics decoding algorithm.
We present a novel framework for applying deep neural networks (DNN) to soft decoding of linear codes at arbitrary block lengths. Unlike other approaches, our framework allows unconstrained DNN design, enabling the free application of powerful designs that were developed in other contexts. Our method is robust to overfitting that inhibits many competing methods, which follows from the exponentially large number of codewords required for their training. We achieve this by transforming the channel output before feeding it to the network, extracting only the syndrome of the hard decisions and the channel output reliabilities. We prove analytically that this approach does not involve any intrinsic performance penalty, and guarantees the generalization of performance obtained during training. Our best results are obtained using a recurrent neural network (RNN) architecture combined with simple preprocessing by permutation. We provide simulation results that demonstrate performance that sometimes approaches that of the ordered statistics decoding (OSD) algorithm.