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

Authors:
Xi-Zhao Wang;Chun-Guo Li;Daniel So Yeung;ShiJi Song;HuiMin Feng
Affiliations:
Department of Mathematics and Computer Science, Hebei University, Baoding, Hebei, China;Department of Mathematics and Computer Science, Hebei University, Baoding, Hebei, China;Department of Computing, Hong Kong Polytechnic University, Kowloon, Hong Kong;Department of Automatization, Tsinghua University, Beijing, China;Department of Mathematics and Computer Science, Hebei University, Baoding, Hebei, China
Venue:
Neurocomputing
Year:
2008

Citing 9
Cited 2

Statistical inference

Statistical inference
Stochastic processes

Stochastic processes
A new algorithm for online structure and parameter adaptation of RBF networks

Neural Networks
Sensitivity analysis applied to the construction of radial basis function networks

Neural Networks
A new definition of sensitivity for RBFNN and its applications to feature reduction

ISNN'05 Proceedings of the Second international conference on Advances in Neural Networks - Volume Part I
Reformulated radial basis neural networks trained by gradient descent

IEEE Transactions on Neural Networks
Sensitivity analysis of multilayer perceptron to input and weight perturbations

IEEE Transactions on Neural Networks
Sensitivity analysis of multilayer perceptron with differentiable activation functions

IEEE Transactions on Neural Networks
The selection of weight accuracies for Madalines

IEEE Transactions on Neural Networks

Architecture selection for networks trained with extreme learning machine using localized generalization error model

Neurocomputing
An optimal weight learning machine for handwritten digit image recognition

Signal Processing

Quantified Score

Hi-index	0.01

Visualization

Abstract

Considering the inputs of a feed-forward neural network as random variables, this paper proposes a definition of partial derivative of a function with respect to a random variable in the probability measure space. The mathematical expectation of the mean square or absolute value of the partial derivative is regarded as a type of measure of the network's sensitivity, which extends Zurada's sensitivity definition of networks in Zurada et al, [Perturbation method for deleting redundant inputs of perceptron networks, Neurocomputing 14 (1997) 177-193] from the certain environment to the stochastic environment. Furthermore, for the purpose of network's redundant feature deletion or feature selection, the new sensitivity measure is applied to the sensitivity analysis of Radial Basis Function Neural Networks (RBFNNs). The feasibility and the effectiveness of the sensitivity approach to redundant feature deletion are illustrated.