Please use this identifier to cite or link to this item:
Title: A study of the difference between partial derivative and stochastic neural network sensitivity analysis for applications in supervised pattern classification problems
Authors: Ng, WY
Yeung, DS
Wang, X
Cloete, I
Keywords: Computational complexity
Feature extraction
Generalisation (artificial intelligence)
Learning (artificial intelligence)
Partial differential equations
Pattern classification
Radial basis function networks
Sampling methods
Sensitivity analysis
Stochastic processes
Issue Date: 2004
Publisher: IEEE
Source: Proceedings of 2004 International Conference on Machine Learning and Cybernetics, 2004, 26-29 August 2004, v. 7, p. 4283-4288 How to cite?
Abstract: This work provides a brief development roadmap of the neural network sensitivity analysis, from 1960's to now on. The two main streams of the sensitivity measures: partial derivative and stochastic sensitivity measures are compared. The partial derivative sensitivity (PD-SM) finds the rate of change of the network output with respect to parameter changes, while the stochastic sensitivity (ST-SM) finds the magnitudes of the output perturbations between the original training samples and the perturbed samples, in statistical sense. Their computational complexities are compared. Furthermore, how to evaluate multiple parameters of the neural network with or without correlation are explored too. In addition, the differences of them in the application of supervised pattern classification problems are also discussed. The evaluations are based on three major applications of sensitivity analysis in supervised pattern classification problems: feature selection, sample selection and neural network generalization assessment. ST-SM and PD-SM of the RBFNN are used for investigations.
ISBN: 0-7803-8403-2
DOI: 10.1109/ICMLC.2004.1384590
Appears in Collections:Conference Paper

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

Page view(s)

Last Week
Last month
Citations as of Dec 16, 2018

Google ScholarTM



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