Study of Sensitivity to Weight Perturbation for Convolution Neural Network

Exploring underlying properties of a neural network contributes to pursuing its internal behavior and functionality. For convolution neural networks (CNNs), a sensitivity measure to weight perturbation is introduced in this paper to reflect the extent of the network output variation, which could eva...

Full description

Bibliographic Details

Published in:	IEEE Access
Main Authors:	Lin Xiang, Xiaoqin Zeng, Yuhu Niu, Yanjun Liu
Format:	Article
Language:	English
Published:	IEEE 2019-01-01
Subjects:	Convolutional neural network sensitivity weight perturbation
Online Access:	https://ieeexplore.ieee.org/document/8755296/