arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1812.01571cs.ITcs.LGmath.IT
收藏

基于深度学习的多级MIMO检测

Multilevel MIMO Detection with Deep Learning

Telecom ParisTech(巴黎高等电信学院);Texas A&M University(得克萨斯农工大学);Mitsubishi Electric R&D(三菱电机研发中心)

Vincent Corlay, Joseph J. Boutros, Philippe Ciblat, Loïc Brunel

摘要:

研究了准静态平坦多天线信道。我们展示了如何通过深度神经网络检测真正的多级调制符号。介绍了一种多平台sigmoid函数。然后,在展示了用于检测的DNN架构之后,我们提出了一种双网络神经结构。研究了有效学习的批量大小和训练统计量。实现了具有相对合理数量的参数的近最大似然性能。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑