Efficient architecture for deep neural networks with heterogeneous sensitivity.

导出 LinkOut

翻译打印收藏纠错

第一作者： Hyunjoong,Cho

第一单位： School of Electrical and Computer Engineering, Ulsan National Institute of Science and Technology (UNIST), Ulsan, Republic of Korea.

作者： Hyunjoong,Cho ^[1] ; Jinhyeok,Jang ^[2] ; Chanhyeok,Lee ^[1] ; Seungjoon,Yang ^[3]

作者单位： School of Electrical and Computer Engineering, Ulsan National Institute of Science and Technology (UNIST), Ulsan, Republic of Korea. ^[1] Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea. ^[2] School of Electrical and Computer Engineering, Ulsan National Institute of Science and Technology (UNIST), Ulsan, Republic of Korea. Electronic address: syang@unist.ac.kr. ^[3]

关键词 Constrained optimization Deep neural networks Efficient architecture Heterogeneous sensitivity Simultaneous regularization parameter selection

主题词数据库, 事实型(Databases, Factual);人类(Humans)

DOI 10.1016/j.neunet.2020.10.017

PMID 33302052

发布时间 2021-03-23

翻译满意度评价：

准确一般字义偏差语意偏离译文作用小提交