ENERGY EFFICIENCY ENHANCEMENT FOR CNN BASED DEEP MOBILE SENSING
ENERGY EFFICIENCY ENHANCEMENT FOR CNN BASED DEEP MOBILE SENSING
复制标题
基于 CNN 的深度移动传感的能源效率增强
DOI：
10.1109/mwc.2019.1800321
复制
发表时间：
2019-06-01
影响因子：
12.9
通讯作者：
Wu, Kaishun
中科院分区：
文献类型：
--
作者：
Xie, Ruitao;Jia, Xiaohua;Wu, Kaishun
最近，深度学习已被用于解决移动传感问题，并且深度学习的推理阶段优选在移动设备上运行以实现快速响应。然而，移动设备是计算和功率方面资源受限的平台。此外，深度学习的推理任务涉及数百亿次数学运算和数千万次参数读取。因此，降低深度学习推理算法的能耗是一个关键问题。在本文中，我们调查了各种节能方法，并将它们分为三类：压缩神经网络模型、最小化计算所需的数据传输以及卸载工作负载。此外，我们通过将三种模型压缩技术应用于对象识别问题来模拟和比较它们。
Recently, deep learning has been used to tackle mobile sensing problems, and the inference phase of deep learning is preferred to be run on mobile devices for speedy responses. However, mobile devices are resource-constrained platforms for both computation and power. Moreover, an inference task with deep learning involves tens of billions of mathematical operations and tens of millions of parameter reads. Thus, it is a critical issue to reduce the energy consumption of deep learning inference algorithms. In this article, we survey various energy reduction approaches, and classify them into three categories: the compressing neural network model, minimizing the data transfer required in computation, and offloading workloads. Moreover, we simulate and compare three techniques of model compression, by applying them to an object recognition problem.