Rethinking pruning for accelerating deep inference at the edge

• Main Authors: GAO, Dawei, HE, Xiaoxi, ZHOU, Zimu, TONG, Yongxin, XU, Ke, THIELE, Lothar
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2020
• Subjects: Deep Learning; Sequence Labelling; Network Pruning; Automatic Speech Recognition; Name Entity Recognition; Databases and Information Systems; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/5292; https://ink.library.smu.edu.sg/context/sis_research/article/6295/viewcontent/3394486.3403058.pdf
• Institution: Singapore Management University

There is a growing trend to deploy deep neural networks at the edge for high-accuracy, real-time data mining and user interaction. Applications such as speech recognition and language understanding often apply a deep neural network to encode an input sequence and then use a decoder to generate the o...