A quasi-static flat multiple-antenna channel is considered. We show how real multilevel modulation symbols can be detected via deep neural networks. A multi-plateau sigmoid function is introduced. Then, after showing the DNN architecture for detection, we propose a twin-network neural structure. Batch size and training statistics for efficient learning are investigated. Near-Maximum-Likelihood performance with a relatively reasonable number of parameters is achieved.
@article{arxiv.1812.01571,
title = {Multilevel MIMO Detection with Deep Learning},
author = {Vincent Corlay and Joseph J. Boutros and Philippe Ciblat and Loïc Brunel},
journal= {arXiv preprint arXiv:1812.01571},
year = {2019}
}
Comments
To Appear in the Proceedings of the 52nd Annual Asilomar Conference on Signals, Systems, and Computers