An Introduction to Deep Learning for the Physical Layer

TLDR

The paper introduces novel deep‑learning applications for the physical layer and outlines future research directions. It models a communication system as an autoencoder, jointly optimizing transmitter and receiver, and extends this framework to multi‑user networks using radio transformer networks that embed expert knowledge. Convolutional neural networks applied to raw IQ samples achieve modulation‑classification accuracy comparable to traditional expert‑feature methods.

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. This paper is concluded with a discussion of open challenges and areas for future investigation.