Learning to communicate: Channel auto-encoders, domain specific regularizers, and attention

We address the problem of learning an efficient and adaptive physical layer encoding to communicate binary information over an impaired channel. In contrast to traditional work, we treat the problem an unsupervised machine learning problem focusing on optimizing reconstruction loss through artificia...

Full description

Saved in:
Bibliographic Details
Published in2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) pp. 223 - 228
Main Authors O'Shea, Timothy J., Karra, Kiran, Clancy, T. Charles
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2016
Subjects
Gaussian noise
Levee
Phase shift keying
Reactive power
Signal to noise ratio
Training
Wireless communication
Online AccessGet full text
DOI10.1109/ISSPIT.2016.7886039

Cover

More Information
Summary:We address the problem of learning an efficient and adaptive physical layer encoding to communicate binary information over an impaired channel. In contrast to traditional work, we treat the problem an unsupervised machine learning problem focusing on optimizing reconstruction loss through artificial impairment layers in an autoencoder (we term this a channel autoencoder) and introduce several new regularizing layers which emulate common wireless channel impairments. We also discuss the role of attention models in the form of the radio transformer network for helping to recover canonical signal representations before decoding. We demonstrate some promising initial capacity results from this approach and address remaining challenges before such a system could become practical.
DOI:10.1109/ISSPIT.2016.7886039