Bayesian Optimization-Based Global Optimal Rank Selection for Compression of Convolutional Neural Networks

Bayesian Optimization-Based Global Optimal Rank Selection for Compression of Convolutional Neural Networks

Recently, convolutional neural network (CNN) compression via low-rank decomposition has achieved remarkable performance. Finding the optimal rank is a crucial problem because rank is the only hyperparameter for controlling computational complexity and accuracy in compressed CNNs. In this paper, we p...

Full description

Bibliographic Details
Main Authors: Taehyeon Kim, Jieun Lee, Yoonsik Choe
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Bayesian optimization
convolutional neural networks
neural network compression
low-rank decomposition
rank selection
Online Access:https://ieeexplore.ieee.org/document/8964358/

Internet

https://ieeexplore.ieee.org/document/8964358/

Similar Items