资源受限的深度学习:挑战与实践  

Resource-constrained deep learning: challenges and practices

作　　者：吴建鑫[1] 高斌斌 魏秀参[1] 罗建豪 Jianxin WU;Bin-Bin GAO;Xiu-Shen WEI;Jian-Hao LUO(National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China)

机构地区：[1]南京大学软件新技术国家重点实验室,南京210023

出　　处：《中国科学：信息科学》2018年第5期501-510,共10页Scientia Sinica(Informationis)

基　　金：国家自然科学基金(批准号:61772256;61422203)资助项目

摘　　要：深度学习近年来取得了突出进展,然而,深度学习模型需要占用大量的与计算相关的资源,同时其学习过程需要大量的数据与标记,因此目前深度学习领域的一个热点是降低其对计算和数据资源的渴求,即研究资源受限的深度学习.本文首先分析深度学习对资源的渴求及其导致的挑战,然后分别从数据、标记、计算资源受限3个方面对目前的研究进展简要描述,并以我们在计算机视觉领域的研究实践为例进行较详细的介绍.Deep learning has made significant progress in recent years. However, deep learning models require many computation-related resources, and their learning process requires a large number of data points and their labels. Hence, the reduction of resource consumption of deep learning, i.e., resource-constrained deep learning, is a current research focus. In this study, we first analyze deep learning＇s thirst for various types of resources and the challenges they lead to and thereafter briefly introduce research progress from three aspects： data, label, and computation resources. Further, we provide detailed introductions of these areas using our research results as examples.

关 键 词：深度学习 资源受限 数据资源 标记资源 计算资源 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]