AirNN: Over-the-Air Computation for Neural Networks via Reconfigurable Intelligent Surfaces
- 14 December 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Networking
- Vol. 31 (6) , 2470-2482
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 convolution that uses over-the-air computation 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 convolutions with over-the-air computation. We then validate the entire resulting CNN model accuracy via simulations for an example task of modulation classification.Keywords
Funding Information
- NSF AI Institute for Future Edge Networks and Distributed Intelligence (CNS-2112471)
- NSF (CNS 1923789, CCF 1937500)
This publication has 36 references indexed in Scilit:
- Over-the-Air Deep Learning Based Radio Signal ClassificationIEEE Journal of Selected Topics in Signal Processing, 2018
- Waveforms classification based on convolutional neural networks2017
- Performance Analysis of GPU-Based Convolutional Neural Networks2016
- XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks2016
- Deep learningNature, 2015
- Gaussian Distribution2012
- Analysis of M-sequence and Gold-sequence in CDMA system2011
- Artificial neural networks in hardware: A survey of two decades of progressNeurocomputing, 2010
- An analog VLSI recurrent neural network learning a continuous-time trajectoryIEEE Transactions on Neural Networks, 1996
- An analog neural network processor with programmable topologyIEEE Journal of Solid-State Circuits, 1991