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

TL;DR

This paper enhances explainable AI in wireless communications by systematically configuring RNN weights with domain knowledge, leading to improved MIMO-OFDM receive processing performance.

Contribution

It introduces a method to incorporate wireless domain knowledge into RNN weights, improving MIMO-OFDM detection performance and interpretability.

Findings

Significant performance improvements in simulations

First-principles understanding of reservoir computing in this context

Framework for integrating domain knowledge into neural network design

Abstract

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.