Sensitivity analysis of multilayer percetron based on elastic function

The sensitivity analysis can help to construct a tightly neural network. There are several methods to define the sensitivity of input and weight for perturbations to the trained neural network. This paper proposed a sensitivity definition based on elastic function. This definition considers the measure of the variable of the reference network. The sensitivity calculating formulae are deduced for perceptron and MLP.

[1]  Daniel S. Yeung,et al.  A Quantified Sensitivity Measure for Multilayer Perceptron to Input Perturbation , 2003, Neural Computation.

[2]  M. Koda.  Neural network learning based on stochastic sensitivity analysis , 1997, IEEE Trans. Syst. Man Cybern. Part B.

[3]  Daniel S. Yeung,et al.  Using function approximation to analyze the sensitivity of MLP with antisymmetric squashing activation function , 2002, IEEE Trans. Neural Networks.

[4]  Ning Xu,et al.  Comparison Study of Sensitivity Definitions of Neural Networks , 2007, 2007 International Conference on Machine Learning and Cybernetics.

[5]  Xizhao Wang,et al.  A New Definition of Sensitivity for RBFNN and Its Applications to Feature Reduction , 2005, ISNN.

[6]  Xizhao Wang,et al.  A definition of partial derivative of random functions and its application to RBFNN sensitivity analysis , 2008, Neurocomputing.

[7]  D.S. Yeung,et al.  Statistical output sensitivity to input and weight perturbations of radial basis function neural networks , 2002, IEEE International Conference on Systems, Man and Cybernetics.

[8]  Chong-Ho Choi,et al.  Sensitivity analysis of multilayer perceptron with differentiable activation functions , 1992, IEEE Trans. Neural Networks.

[9]  Tülay Yildirim,et al.  Sensitivity analysis for conic section function neural networks , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[10]  Daniel S. Yeung,et al.  Hidden neuron pruning of multilayer perceptrons using a quantified sensitivity measure , 2006, Neurocomputing.

[11]  G. Lewicki,et al.  Approximation by Superpositions of a Sigmoidal Function , 2003 .

[12]  Steve W. Piche,et al.  The selection of weight accuracies for Madalines , 1995, IEEE Trans. Neural Networks.

[13]  D.S. Yeung,et al.  Input dimensionality reduction for radial basis neural network classification problems using sensitivity measure , 2002, Proceedings. International Conference on Machine Learning and Cybernetics.

[14]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[15]  Daniel S. Yeung,et al.  Sensitivity analysis of multilayer perceptron to input and weight perturbations , 2001, IEEE Trans. Neural Networks.

[16]  Daming Shi,et al.  Sensitivity analysis applied to the construction of radial basis function networks , 2005, Neural Networks.

[17]  Bernard Widrow,et al.  Sensitivity of feedforward neural networks to weight errors , 1990, IEEE Trans. Neural Networks.

[18]  Daniel S. Yeung,et al.  Sensitivity analysis of neocognitron , 1999, IEEE Trans. Syst. Man Cybern. Part C.

[19]  Daniel S. Yeung,et al.  Dimensionality reduction for denial of service detection problems using RBFNN output sensitivity , 2003, Proceedings of the 2003 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.03EX693).

[20]  Jacek M. Zurada,et al.  Perturbation method for deleting redundant inputs of perceptron networks , 1997, Neurocomputing.