Resource-constrained deep learning: challenges and practices
Jianxin Wu, Bin-Bin Gao, Xiu-Shen Wei, Jian-Hao Luo · Scientia Sinica Informationis · 2018
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 learnings 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.