Paper Info
Title
A quantified sensitivity measure of Radial Basis Function Neural Networks to input variation
Abstract
The sensitivity of a neural network's output to its parameter variation is an important issue in both theoretical researches and practical applications of neural networks. This paper proposes a quantified sensitivity measure of the Radial Basis Function Neural Networks (RBFNNs) to input variation. The sensitivity is defined as the mathematical expectation of squared output deviations caused by input variations. In order to quantify the sensitivity, the input is treated as a statistical variable and a numerical integral technique is employed to approximately compute the expectation. Experimental verifications are run and the results show a very good agreement between the proposed sensitivity computation and computer simulation. The quantified sensitivity measure could be helpful as a general tool for evaluating RBFNNs' performance.
Year
DOI
Venue
2010
10.1109/IJCNN.2010.5596949
IJCNN
Keywords
Field
DocType
integral equations,radial basis function networks,quantified sensitivity measure,statistical analysis,learning (artificial intelligence),numerical integral technique,sensitivity computation,radial basis function neural networks,rbfnn,computer simulation,sensitivity analysis,function approximation,computational modeling,artificial neural networks,computer architecture,numerical integration,neural network,learning artificial intelligence,sensitivity
Square (algebra),Pattern recognition,Function approximation,Computer science,Radial basis function neural,Integral equation,Expected value,Artificial intelligence,Artificial neural network,Machine learning,Statistical analysis,Computation
Conference
Volume
Issue
ISSN
null
null
1098-7576
ISBN
Citations 
PageRank 
978-1-4244-6916-1
0
0.34
References 
Authors
13
4
Name
Order
Citations
PageRank
Xianming Chen100.34
Xiaoqin Zeng240732.97
Rong Chu351.80
Shuiming Zhong4797.30