Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/33598
Title: A quantified sensitivity measure for multilayer perceptron to input perturbation
Authors: Zeng, X
Yeung, DS
Issue Date: 2003
Source: Neural computation, 2003, v. 15, no. 1, p. 183-212 How to cite?
Journal: Neural Computation 
Abstract: The sensitivity of a neural network's output to its input perturbation is an important issue with both theoretical and practical values. In this article, we propose an approach to quantify the sensitivity of the most popular and general feedforward network: multilayer perceptron (MLP). The sensitivity measure is defined as the mathematical expectation of output deviation due to expected input deviation with respect to overall input patterns in a continuous interval. Based on the structural characteristics of the MLP, a bottom-up approach is adopted. A single neuron is considered first, and algorithms with approximately derived analytical expressions that are functions of expected input deviation are given for the computation of its sensitivity. Then another algorithm is given to compute the sensitivity of the entire MLP network. Computer simulations are used to verify the derived theoretical formulas. The agreement between theoretical and experimental results is quite good. The sensitivity measure can be used to evaluate the MLP's performance.
URI: http://hdl.handle.net/10397/33598
ISSN: 0899-7667
DOI: 10.1162/089976603321043757
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

41
Last Week
0
Last month
0
Citations as of Aug 17, 2017

WEB OF SCIENCETM
Citations

35
Last Week
0
Last month
Citations as of Aug 15, 2017

Page view(s)

30
Last Week
2
Last month
Checked on Aug 13, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.