Sparsing Deep Neural Network Using Semi-Discrete Matrix Decomposition

Sparsing Deep Neural Network Using Semi-Discrete Matrix Decomposition

Deep learning has gained a lot of successes in various areas, including computer vision, natural language process, and robot control. Convolution neural network (CNN) is the most commonly used model in deep neural networks. Despite their effectiveness on feature abstraction, CNNs need powerful compu...

Full description

Bibliographic Details
Main Authors: Xianya Fu, Peixuan Zuo, Jia Zhai, Rui Wang, Hailong Yang, Depei Qian
Format: Article
Language:English
Published: IEEE 2018-01-01
Series:IEEE Access
Subjects:
Deep neural network
sparsity
matrix decomposition
memory footprints
Online Access:https://ieeexplore.ieee.org/document/8478113/

Similar Items

Similar Items