A Novel Deep Learning Model Compression Algorithm

In order to solve the problem of large model computing power consumption, this paper proposes a novel model compression algorithm. Firstly, this paper proposes an interpretable weight allocation method for the loss between a student network (a network model with poor performance), a teacher network...

Full description

Bibliographic Details

Published in:	Electronics (Basel) Vol. 11; no. 7; p. 1066
Main Authors:	Zhao, Ming, Li, Meng, Peng, Sheng-Lung, Li, Jie
Format:	Journal Article
Language:	English
Published:	Basel MDPI AG 01.04.2022
Subjects:	20th century Accuracy Algorithms Deep learning Distillation Knowledge Machine learning Model accuracy Neural networks Power consumption Probability distribution Teachers
ISSN:	2079-9292, 2079-9292
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!