AirNN: Over-the-Air Computation for Neural Networks via Reconfigurable Intelligent Surfaces
AirNN: Over-the-Air Computation for Neural Networks via Reconfigurable Intelligent Surfaces
复制标题
DOI：
10.1109/tnet.2022.3225883
复制
发表时间：
2023-12
期刊：
影响因子：
--
通讯作者：
Sara Garcia Sanchez;Guillem Reus-Muns;Carlos Bocanegra;Yanyu Li;Ufuk Muncuk;Yousof Naderi;Yanzhi Wang;Stratis Ioannidis;K. Chowdhury
中科院分区：
文献类型：
--
作者：
Sara Garcia Sanchez;Guillem Reus-Muns;Carlos Bocanegra;Yanyu Li;Ufuk Muncuk;Yousof Naderi;Yanzhi Wang;Stratis Ioannidis;K. Chowdhury
空中模拟计算允许通过精心构建的传输信号将计算卸载到无线环境。在这篇文章中，我们设计并实现了第一个使用空中计算的卷积，并在卷积神经网络(CNN)的推理任务中演示了它。我们通过可重构智能表面(RIS)来设计环境无线传播环境，从而设计出这样一种体系结构，我们称之为‘AirNN’。AirNN利用波反射的物理原理在模拟域中表示数字卷积，这是CNN架构的重要组成部分。与传统通信不同，在传统通信中，接收方必须对通常表示为有限脉冲响应(FIR)滤波器的信道诱导变换做出反应，而AirNN通过RIS主动创建信号反射来模拟特定的FIR滤波器。AirNN包括两个步骤：首先，从与可实现的FIR滤波器相对应的有限的信道冲激响应(CIR)集合中提取CNN中神经元的权重。其次，通过RIS设计每个CIR，并且在接收器处组合反射信号以确定卷积的输出。本文通过实验演示卷积和空中计算，提出了一种空中神经网络的概念证明。然后，我们通过对一个调制分类的示例任务的仿真来验证整个得到的CNN模型的准确性。
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.