We explore unsupervised representation learning of radio communication signals in raw sampled time series representation. We demonstrate that we can learn modulation basis functions using convolutional autoencoders and visually recognize their relationship to the analytic bases used in digital communications. We also propose and evaluate quantitative met- rics for quality of encoding using domain relevant performance metrics.
@article{arxiv.1604.07078,
title = {Unsupervised Representation Learning of Structured Radio Communication Signals},
author = {Timothy J. O'Shea and Johnathan Corgan and T. Charles Clancy},
journal= {arXiv preprint arXiv:1604.07078},
year = {2016}
}
Comments
4 pages, 9 figures, currently under conference submission