An Introduction to Deep Learning for the Physical Layer
This work addresses the challenge of improving physical layer communications for researchers and engineers by introducing a new paradigm that integrates deep learning, though it is foundational and not incremental.
The paper tackles the problem of communications system design by reinterpreting it as an end-to-end reconstruction task using autoencoders, resulting in a novel approach that jointly optimizes transmitter and receiver components and extends to networks with competitive accuracy in modulation classification.
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.