Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/11827
Title: Using function approximation to analyze the sensitivity of MLP with antisymmetric squashing activation function
Authors: Yeung, DS
Sun, X
Keywords: Antisymmetric squashing activation activation
Multilayer perceptron
Network design parameters and construction
Sensitivity analysis
Issue Date: 2002
Publisher: Institute of Electrical and Electronics Engineers
Source: IEEE transactions on neural networks, 2002, v. 13, no. 1, p. 34-44 How to cite?
Journal: IEEE transactions on neural networks 
Abstract: Sensitivity analysis on a neural network is mainly investigated after the network has been designed and trained. Very few have considered this as a critical issue prior to network design. Piché's statistical method is useful for multilayer perceptron (MLP) design, but too severe limitations are imposed on both input and weight perturbations. This paper attempts to generalize Piché's method by deriving an universal expression of MLPs sensitivity for antisymmetric squashing activation functions, without any restriction on input and output perturbations. Experimental results which are based on a three-layer MLP with 30 nodes per layer agree closely with our theoretical investigations. The effects of the network design parameters such as the number of layers, the number of neurons per layer, and the chosen activation function are analyzed, and they provide useful information for network design decision-making. Based on the sensitivity analysis of MLP, we present a network design method for a given application to determine the network structure and estimate the permitted weight range for network training.
URI: http://hdl.handle.net/10397/11827
ISSN: 1045-9227
DOI: 10.1109/72.977266
Appears in Collections:Journal/Magazine Article

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

SCOPUSTM   
Citations

40
Last Week
0
Last month
0
Citations as of Oct 11, 2017

WEB OF SCIENCETM
Citations

29
Last Week
0
Last month
0
Citations as of Oct 17, 2017

Page view(s)

41
Last Week
1
Last month
Checked on Oct 15, 2017

Google ScholarTM

Check

Altmetric



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