AirNN: Neural Networks with Over-the-Air Convolution via Reconfigurable Intelligent Surfaces

TL;DR

AirNN introduces a novel method to perform neural network convolution operations over-the-air using reconfigurable intelligent surfaces to engineer wireless signals, enabling efficient analog computation for inference tasks.

Contribution

This paper pioneers the design and experimental demonstration of over-the-air convolution in CNNs using RIS to engineer wireless propagation environments.

Findings

Successfully demonstrated over-the-air convolution via RIS

Validated CNN inference accuracy through simulations

Proposed a new architecture for analog neural network computation

Abstract

Over-the-air analog computation allows offloading computation to the wireless environment through carefully constructed transmitted signals. In this paper, we design and implement the first-of-its-kind over-the-air convolution and demonstrate it for inference tasks in a convolutional neural network (CNN). We engineer the ambient wireless propagation environment through reconfigurable intelligent surfaces (RIS) to design such an architecture, which we call 'AirNN'. AirNN leverages the physics of wave reflection to represent a digital convolution, an essential part of a CNN architecture, in the analog domain. In contrast to classical communication, where the receiver must react to the channel-induced transformation, generally represented as finite impulse response (FIR) filter, AirNN proactively creates the signal reflections to emulate specific FIR filters through RIS. AirNN involves two steps: first, the weights of the neurons in the CNN are drawn from a finite set of channel impulse responses (CIR) that correspond to realizable FIR filters. Second, each CIR is engineered through RIS, and reflected signals combine at the receiver to determine the output of the convolution. This paper presents a proof-of-concept of AirNN by experimentally demonstrating over-the-air convolutions. We then validate the entire resulting CNN model accuracy via simulations for an example task of modulation classification.