arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.02750cs.ITcs.LGeess.SPmath.IT
收藏

深度HyperNetwork-Based MIMO检测

Deep HyperNetwork-Based MIMO Detection

Nokia Bell Labs(诺基亚贝尔实验室);Univ Lyon(里昂大学);INSA Lyon(里昂国立应用科学学院);Inria(法国国家信息与自动化研究所)

Mathieu Goutay, Fayçal Ait Aoudia, Jakob Hoydis

摘要:

多输入多输出(MIMO)系统的最优符号检测是一个NP难题。传统的启发式算法要么太复杂而不实用,要么性能很差。最近,有几种方法试图通过将检测器实现为深度神经网络来解决这些挑战。然而,它们在实际空间相关信道上仍然实现不令人满意的性能,或者由于它们需要针对每个信道实现进行再训练而在计算上要求很高。在这项工作中,我们解决这两个问题,通过训练一个额外的神经网络(NN),被称为超网络,它作为输入的信道矩阵和生成的神经NN为基础的检测器的权重。结果表明,所提出的方法实现了接近国家的最先进的性能,而不需要重新训练。

英文摘要:

Optimal symbol detection for multiple-input multiple-output (MIMO) systems is known to be an NP-hard problem. Conventional heuristic algorithms are either too complex to be practical or suffer from poor performance. Recently, several approaches tried to address those challenges by implementing the detector as a deep neural network. However, they either still achieve unsatisfying performance on practical spatially correlated channels, or are computationally demanding since they require retraining for each channel realization. In this work, we address both issues by training an additional neural network (NN), referred to as the hypernetwork, which takes as input the channel matrix and generates the weights of the neural NN-based detector. Results show that the proposed approach achieves near state-of-the-art performance without the need for re-training.

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。

↑