Deep Architectures for Modulation Recognition

TL;DR

This paper surveys recent deep learning methods applied to radio modulation recognition, highlighting that network depth isn't the limiting factor and emphasizing the need for improved synchronization and equalization techniques.

Contribution

It provides an overview of current deep neural network approaches for modulation recognition and identifies key areas for future research to enhance performance.

Findings

Network depth does not limit modulation recognition performance.

Future improvements depend on better synchronization and equalization.

Novel architectures and training methods are needed for progress.

Abstract

We survey the latest advances in machine learning with deep neural networks by applying them to the task of radio modulation recognition. Results show that radio modulation recognition is not limited by network depth and further work should focus on improving learned synchronization and equalization. Advances in these areas will likely come from novel architectures designed for these tasks or through novel training methods.