Learning and Compressing: Low-Rank Matrix Factorization for Deep Neural Network Compression

Learning and Compressing: Low-Rank Matrix Factorization for Deep Neural Network Compression

Recently, the deep neural network (DNN) has become one of the most advanced and powerful methods used in classification tasks. However, the cost of DNN models is sometimes considerable due to the huge sets of parameters. Therefore, it is necessary to compress these models in order to reduce the para...

Full description

Bibliographic Details
Main Authors: Gaoyuan Cai, Juhu Li, Xuanxin Liu, Zhibo Chen, Haiyan Zhang
Format: Article
Language:English
Published: MDPI AG 2023-02-01
Series:Applied Sciences
Subjects:
deep neural network compression
low-rank matrix factorization
truncated singular value decomposition
CUR decomposition
joint optimization
optimal rank
Online Access:https://www.mdpi.com/2076-3417/13/4/2704

Internet

https://www.mdpi.com/2076-3417/13/4/2704

Similar Items