Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/34359
Title: Sensitivity analysis of multilayer perceptron to input and weight perturbations
Authors: Zeng, X
Yeung, DS
Keywords: Multilayer perception (MLP)
Neural networks
Sensitivity analysis
Issue Date: 2001
Publisher: Institute of Electrical and Electronics Engineers
Source: IEEE transactions on neural networks, 2001, v. 12, no. 6, p. 1358-1366 How to cite?
Journal: IEEE transactions on neural networks 
Abstract: An important issue in the design and implementation of a neural network is the sensitivity of its output to input and weight perturbations. In this paper, we discuss the sensitivity of the most popular and general feedforward neural networks-multilayer perception (MLP). The sensitivity is defined as the mathematical expectation of the output errors of the MLP due to input and weight perturbations with respect to all input and weight values in a given continuous interval. The sensitivity for a single neuron is discussed first and an analytical expression that is a function of the absolute values of input and weight perturbations is approximately derived. Then an algorithm is given to compute the sensitivity for the entire MLP. As intuitively expected, the sensitivity increases with input and weight perturbations, but the increase has an upper bound that is determined by the structural configuration of the MLP, namely the number of neurons per layer and the number of layers. There exists an optimalvalue for the number of neurons in a layer, which yields the highest sensitivity value. The effect caused by the number of layers is quite unexpected. The sensitivity of a neural network may decrease at first and then almost keeps constant while the number increases.
URI: http://hdl.handle.net/10397/34359
ISSN: 1045-9227
DOI: 10.1109/72.963772
Appears in Collections:Journal/Magazine Article

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

SCOPUSTM   
Citations

68
Last Week
0
Last month
1
Citations as of Oct 11, 2017

WEB OF SCIENCETM
Citations

51
Last Week
0
Last month
0
Citations as of Oct 16, 2017

Page view(s)

40
Last Week
1
Last month
Checked on Oct 16, 2017

Google ScholarTM

Check

Altmetric



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