A Learning-Based Approach to Address Complexity-Reliability Tradeoff in OS Decoders

TL;DR

This paper proposes a neural network-based method to optimize the complexity-reliability tradeoff in OS decoders, reducing latency in decoding large linear block codes through predictive modeling validated by simulations.

Contribution

It introduces a learning-based technique that uses neural networks to predict decoder order, improving efficiency over traditional methods.

Findings

Reduced average complexity and latency in decoding

Neural network predictions improve decoding efficiency

Validated approach through Monte Carlo simulations

Abstract

In this paper, we study the tradeoffs between complexity and reliability for decoding large linear block codes. We show that using artificial neural networks to predict the required order of an ordered statistics based decoder helps in reducing the average complexity and hence the latency of the decoder. We numerically validate the approach through Monte Carlo simulations.