A definition of partial derivative of random functions and its application to RBFNN sensitivity analysis

Neurocomputing

Volumn 71, Issue 7-9, 2008, Pages 1515-1526

  Wang, Xi Zhao ^a   Li, Chun Guo ^a   Yeung, Daniel So ^b   Song, ShiJi ^c   Feng, HuiMin ^a  

^a HEBEI UNIVERSITY   (China)

^b HONG KONG POLYTECHNIC UNIVERSITY   (Hong Kong)

^c TSINGHUA UNIVERSITY   (China)

Author keywords

Feature selection; Mathematical expectation; Partial derivative of a random variable; Probability measure space; RBFNN; Sensitivity measure

Indexed keywords

FEATURE EXTRACTION; PARTIAL DIFFERENTIAL EQUATIONS; RANDOM PROCESSES; RANDOM VARIABLES; SENSITIVITY ANALYSIS;

MATHEMATICAL EXPECTATION; PARTIAL DERIVATIVE; PROBABILITY MEASURE SPACE; SENSITIVITY MEASURE;

RADIAL BASIS FUNCTION NETWORKS;

ARTICLE; CALCULATION; FEASIBILITY STUDY; MATHEMATICAL COMPUTING; NORMAL DISTRIBUTION; PERCEPTRON; PRIORITY JOURNAL; PROBABILITY; RADIAL BASED FUNCTION; SENSITIVITY ANALYSIS; STATISTICAL ANALYSIS;

EID: 40649105766     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2007.05.005     Document Type: Article

References (17)

1. Alexandridis A., Sarimveis H., and Bafas G. A new algorithm for online structure and parameter adaptation of RBF networks. Neural networks 16 (2003) 1003-1017
2. Karayiannis N.B. Reformulated radial basis neural networks trained by gradient decent. IEEE Transactions on Neural Networks 10 3 (1999) 657-671
3. X. Wang, C. Li, A new definition of sensitivity for RBFNN and its applications to feature reduction, in Second International Symposium on Neural Networks, LNCS 3496, pp. 81-86, 2005.
4. W.Y.N.G. Wing, D.S. Yeung, Input dimensionality reduction for Radial Basis Neural Network classification problems using sensitivity analysis, in: Proceedings of the First International Conference on Machine Learning and Cybernetics, 2002, pp. 2214-2219.
5. Shi D., Yeung D.S., and Gao J. Sensitivity analysis applied to the construction of radial basis function networks. Neural Networks 18 (2005) 951-957
6. Zurada J.M., Malinowski A., and Usui S. Perturbation method for deleting redundant inputs of perceptron networks. Neurocomputing 14 (1997) 177-193
7. Dudley R.M. Real Analysis and Probability (2002), Cambridge University Press, Cambridge, New York
8. Garthwaite P.H. Statistical Inference (2002), Oxford University Press, Oxford, New York
9. P.R. Halmos, Measure Theory, New York, 1950.
10. Choi J.Y., and Choi C.-H. Sensitivity analysis of multilayer perceptron with differentiable activation functions. IEEE Transactions on Neural Networks 3 1 (1992) 101-107
11. Zeng X., and Yeung D.S. Sensitivity analysis of multilayer perceptron to input and weight perturbations. IEEE Transactions on Neural Networks 12 6 (2001) 1358-1366
12. Piché S.W. The selection of weight accuracies for madalines. IEEE Transactions on Neural Networks 6 2 (1995) 432-445
13. L. Xu, et al., Mathematic Dictionary, ShanXi Educational Publishing Company, Southeast University Publishing Company, Science and Technology Publishing Company of China, Vol. 4, August 2002, p. 371.
14. Z. Sheng, S. Xie, C. Pan, Probability Theory and Mathematical Statistics, third ed., Higher Education Publishing Company, 2001.12. pp. 241-253.
15. C. Lin, Numerical Calculating Methodology, Vol. 1, Science Publishing Company. 2000.8. pp. 178-180.
16. Parzen E. Stochastic Processes (1999), Society for Industrial and Applied Mathematics, Philadelphia, PA, USA
17. http://www.icmlc.org/bsdata.htm