面向物联网的压缩深度神经网络：方法与应用
Compacting Deep Neural Networks for Internet of Things: Methods and Applications
摘要：
深度神经网络（DNN）在完成复杂任务方面取得了巨大成功。然而，由于层次结构的复杂性，DNN不可避免地带来高计算成本和存储消耗，从而阻碍了它们在具有有限计算能力和存储容量的物联网（IoT）设备中的广泛部署。因此，有必要研究压缩DNN的技术。尽管在压缩DNN方面取得了巨大的进步，但很少有调查总结压缩DNN技术，特别是对于物联网应用。因此，本文提出了一个全面的研究，对分布式神经网络技术。我们将分布式神经网络技术分为三种主要类型：1）网络模型压缩，2）知识蒸馏（KD），3）网络结构的修改。我们还详细阐述了这些方法的多样性，并进行并排比较。此外，我们还讨论了压缩DNN在各种物联网应用中的应用，并概述了未来的发展方向。
英文摘要：
Deep Neural Networks (DNNs) have shown great success in completing complex tasks. However, DNNs inevitably bring high computational cost and storage consumption due to the complexity of hierarchical structures, thereby hindering their wide deployment in Internet-of-Things (IoT) devices, which have limited computational capability and storage capacity. Therefore, it is a necessity to investigate the technologies to compact DNNs. Despite tremendous advances in compacting DNNs, few surveys summarize compacting-DNNs technologies, especially for IoT applications. Hence, this paper presents a comprehensive study on compacting-DNNs technologies. We categorize compacting-DNNs technologies into three major types: 1) network model compression, 2) Knowledge Distillation (KD), 3) modification of network structures. We also elaborate on the diversity of these approaches and make side-by-side comparisons. Moreover, we discuss the applications of compacted DNNs in various IoT applications and outline future directions.
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。
