An Introduction to Deep Learning for the Physical Layer

TL;DR

This paper explores innovative deep learning applications in the physical layer of communications, framing systems as autoencoders, and demonstrating neural network-based modulation classification with promising results.

Contribution

It introduces a new end-to-end deep learning framework for communication systems, including radio transformer networks and raw IQ sample classification.

Findings

Autoencoder-based communication system design

Radio transformer networks incorporate domain knowledge

CNNs achieve competitive modulation classification accuracy

Abstract

We present and discuss several novel applications of deep learning for the physical layer. By interpreting a communications system as an autoencoder, we develop a fundamental new way to think about communications system design as an end-to-end reconstruction task that seeks to jointly optimize transmitter and receiver components in a single process. We show how this idea can be extended to networks of multiple transmitters and receivers and present the concept of radio transformer networks as a means to incorporate expert domain knowledge in the machine learning model. Lastly, we demonstrate the application of convolutional neural networks on raw IQ samples for modulation classification which achieves competitive accuracy with respect to traditional schemes relying on expert features. The paper is concluded with a discussion of open challenges and areas for future investigation.