arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2304.07378cs.AR
收藏

一种用于实现微波人工神经网络的可重构线性射频模拟处理器

A Reconfigurable Linear RF Analog Processor for Realizing Microwave Artificial Neural Network

Minning Zhu, Tzu-Wei Kuo, Chung-Tse Michael Wu

AI总结:

提出一种2X2可重构线性射频模拟处理器作为人工神经网络的矩阵乘法器,构建RFNN实现数据分类,并在4层ANN上完成MNIST数据集分类。

摘要:

由于数据的爆炸性增长和人工智能(AI)的快速发展,特别是深度神经网络(DNNs),对大规模矩阵向量乘法日益增长的需求已成为机器学习(ML)中的主要问题之一。训练和评估此类神经网络依赖大量计算资源,导致显著的系统延迟和功耗。为了克服这些问题,使用基于光学干涉的线性处理器的模拟计算最近作为加速矩阵向量乘法和降低功耗的有前途的候选者出现。另一方面,射频(RF)电磁波也可以通过以光速进行模拟计算并具有较低功耗,展现出与光学对应物类似的优势。此外,射频设备具有额外的优势,如更低的成本、成熟的制造工艺和模数混合设计的简单性,这在实现经济实惠、可扩展、低延迟、低功耗、近传感器的射频神经网络(RFNN)方面具有巨大潜力,可能极大地丰富射频信号处理能力。在这项工作中,我们在理论和实验上提出了一种2X2可重构线性射频模拟处理器,可作为人工神经网络(ANN)中的矩阵乘法器。所提出的设备可用于实现一个2X2简单RFNN进行数据分类。由28个RFNN设备组成的8X8线性模拟处理器也被应用于一个4层ANN中,用于修改版国家标准与技术研究院(MNIST)数据集分类。

英文摘要:

Owing to the data explosion and rapid development of artificial intelligence (AI), particularly deep neural networks (DNNs), the ever-increasing demand for large-scale matrix-vector multiplication has become one of the major issues in machine learning (ML). Training and evaluating such neural networks rely on heavy computational resources, resulting in significant system latency and power consumption. To overcome these issues, analog computing using optical interferometric-based linear processors have recently appeared as promising candidates in accelerating matrix-vector multiplication and lowering power consumption. On the other hand, radio frequency (RF) electromagnetic waves can also exhibit similar advantages as the optical counterpart by performing analog computation at light speed with lower power. Furthermore, RF devices have extra benefits such as lower cost, mature fabrication, and analog-digital mixed design simplicity, which has great potential in realizing affordable, scalable, low latency, low power, near-sensor radio frequency neural network (RFNN) that may greatly enrich RF signal processing capability. In this work, we propose a 2X2 reconfigurable linear RF analog processor in theory and experiment, which can be applied as a matrix multiplier in an artificial neural network (ANN). The proposed device can be utilized to realize a 2X2 simple RFNN for data classification. An 8X8 linear analog processor formed by 28 RFNN devices are also applied in a 4-layer ANN for Modified National Institute of Standards and Technology (MNIST) dataset classification.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑