arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.01539cs.LGeess.IVstat.ML
收藏

在边缘发生的事情,保持在边缘:迈向压缩式深度学习

What Happens on the Edge, Stays on the Edge: Toward Compressive Deep Learning

University of California, Davis(加州大学戴维斯分校)

Yang Li, Thomas Strohmer

摘要:

边缘的机器学习提供了巨大的好处,例如提高隐私和安全性,低延迟和更多的自主性。然而,一个主要的挑战是,许多设备,特别是边缘设备,内存非常有限,处理器很弱,能源供应不足。我们提出了一种混合硬件-软件框架,该框架有可能显著降低设备上机器学习的计算复杂性和内存需求。在第一步中,受压缩感测的启发,数据以压缩形式与感测过程同时收集。因此,这种压缩在数据采集期间已经在硬件级别发生。但与压缩感测不同的是,这种压缩是通过专门针对所需机器学习任务定制的投影算子实现的。第二步由专门设计和训练的深度网络组成。作为具体的例子,我们认为图像分类的任务,虽然所提出的框架是更广泛的适用。我们的方法的另一个好处是,它可以很容易地与现有的设备上的技术相结合。数值模拟说明了我们的方法的可行性。

英文摘要:

Machine learning at the edge offers great benefits such as increased privacy and security, low latency, and more autonomy. However, a major challenge is that many devices, in particular edge devices, have very limited memory, weak processors, and scarce energy supply. We propose a hybrid hardware-software framework that has the potential to significantly reduce the computational complexity and memory requirements of on-device machine learning. In the first step, inspired by compressive sensing, data is collected in compressed form simultaneously with the sensing process. Thus this compression happens already at the hardware level during data acquisition. But unlike in compressive sensing, this compression is achieved via a projection operator that is specifically tailored to the desired machine learning task. The second step consists of a specially designed and trained deep network. As concrete example we consider the task of image classification, although the proposed framework is more widely applicable. An additional benefit of our approach is that it can be easily combined with existing on-device techniques. Numerical simulations illustrate the viability of our method.

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。

↑