arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.07072eess.SPcs.LG
收藏

迈向xAI:利用领域知识配置用于MIMO接收处理的RNN权重

Towards xAI: Configuring RNN Weights using Domain Knowledge for MIMO Receive Processing

Virginia Tech(弗吉尼亚理工大学);Massachusetts Institute of Technology(麻省理工学院)

Shashank Jere, Lizhong Zheng, Karim Said, Lingjia Liu

AI总结:

本研究针对无线通信物理层深度学习可解释性不足的问题,基于信号处理原理阐释储层计算的运行机制,将信道统计等领域知识融入RNN权重配置,提升MIMO-OFDM符号检测性能,为NextG可解释神经网络设计提供参考。

摘要:

深度学习正在对无线通信物理层产生深远影响。尽管深度学习在MIMO接收处理等任务中展现出优异的实证性能,但其性能提升背后的原因在很大程度上仍不明确。在本研究中,我们利用信号处理原理推动无线通信物理层领域的可解释人工智能(Explainable AI, xAI)发展。具体而言,我们聚焦于采用储层计算(reservoir computing, RC,一种循环神经网络(recurrent neural networks, RNNs)框架)的MIMO-OFDM接收处理(例如符号检测)任务,该方法的性能优于传统MIMO检测器及其他基于学习的MIMO检测器。我们的分析从信号处理的第一性原理出发,阐释了RC对应运行机制的原理。基于这一基础认知,我们能够通过直接配置用于MIMO-OFDM符号检测的未训练RNN权重,将无线系统的领域知识(例如信道统计特性)系统性地融入底层RNN的设计中。大量仿真验证了所提出的RNN权重配置方法,结果表明其性能提升显著。本研究为MIMO-OFDM接收处理中基于RC的可解释架构奠定了基础,并为将领域知识融入NextG系统的神经网络设计提供了路线图。

英文摘要:

Deep learning is making a profound impact in the physical layer of wireless communications. Despite exhibiting outstanding empirical performance in tasks such as MIMO receive processing, the reasons behind the demonstrated superior performance improvement remain largely unclear. In this work, we advance the field of Explainable AI (xAI) in the physical layer of wireless communications utilizing signal processing principles. Specifically, we focus on the task of MIMO-OFDM receive processing (e.g., symbol detection) using reservoir computing (RC), a framework within recurrent neural networks (RNNs), which outperforms both conventional and other learning-based MIMO detectors. Our analysis provides a signal processing-based, first-principles understanding of the corresponding operation of the RC. Building on this fundamental understanding, we are able to systematically incorporate the domain knowledge of wireless systems (e.g., channel statistics) into the design of the underlying RNN by directly configuring the untrained RNN weights for MIMO-OFDM symbol detection. The introduced RNN weight configuration has been validated through extensive simulations demonstrating significant performance improvements. This establishes a foundation for explainable RC-based architectures in MIMO-OFDM receive processing and provides a roadmap for incorporating domain knowledge into the design of neural networks for NextG systems.

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。

↑