Implementing Neural Networks Over-the-Air via Reconfigurable Intelligent Surfaces

TL;DR

This paper introduces AirFC, a novel RIS-aided MIMO system that emulates neural network fully-connected layers over-the-air, optimizing wireless environment parameters for efficient neural network computation.

Contribution

It proposes a new RIS-based over-the-air neural network implementation with joint optimization and training strategies, including centralized and distributed methods, and extends to multi-RIS scenarios.

Findings

Achieves satisfactory classification accuracy with the proposed RIS-aided MIMO system.

Develops low-complexity algorithms for joint optimization of system parameters.

Demonstrates improved performance through multi-RIS spatial diversity.

Abstract

In this paper, we investigate reconfigurable intelligent surface (RIS)-aided multiple-input-multiple-output (MIMO) OAC systems designed to emulate the fully-connected (FC) layer of a neural network (NN) via analog OAC, where the RIS and the transceivers are jointly adjusted to engineer the ambient wireless propagation environment to emulate the weights of the target FC layer. We refer to this novel computational paradigm as AirFC. We first study the case in which the precoder, combiner, and RIS phase shift matrices are jointly optimized to minimize the mismatch between the OAC system and the target FC layer. To solve this non-convex optimization problem, we propose a low-complexity alternating optimization algorithm, where semi-closed-form/closed-form solutions for all optimization variables are derived. Next, we consider training of the system parameters using two distinct learning strategies, namely centralized training and distributed training. In the centralized training approach, training is performed at either the transmitter or the receiver, whichever possesses the channel state information (CSI), and the trained parameters are provided to the other terminal. In the distributed training approach, the transmitter and receiver iteratively update their parameters through back and forth transmissions by leveraging channel reciprocity, thereby avoiding CSI acquisition and significantly reducing computational complexity. Subsequently, we extend our analysis to a multi-RIS scenario by exploiting its spatial diversity gain to enhance the system performance. Simulation results show that the AirFC system realized by the RIS-aided MIMO configuration achieves satisfactory classification accuracy.