Sensitivity analysis for feedforward artificial neural networks with differentiable activation functions

A method for computing the network output sensitivities with respect to variations in the inputs for multilayer feedforward artificial neural networks with differentiable activation functions is presented. It is applied to obtain expressions for the first- and second-order sensitivities. An example is introduced along with a discussion to illustrate how the sensitivities are calculated and to show how they compare to the actual derivatives of the function being modeled by the neural network.<<ETX>>

[1]  Kurt Hornik,et al.  Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks , 1990, Neural Networks.

[2]  Hecht-Nielsen.  Theory of the backpropagation neural network , 1989 .

[3]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[4]  A. Agogino,et al.  Use of influence diagrams and neural networks in modeling LPCVD , 1990, IEEE/SEMI International Symposium on Semiconductor Manufacturing Science.

[5]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[6]  Richard S. Sutton,et al.  Learning a nonlinear model of a manufacturing process using multilayer connectionist networks , 1990, Proceedings. 5th IEEE International Symposium on Intelligent Control 1990.

[7]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[8]  Deborah F. Cook,et al.  A sensitivity analysis of a back-propagation neural network for manufacturing process parameters , 1991, J. Intell. Manuf..

[9]  N.V. Bhat,et al.  Modeling chemical process systems via neural computation , 1990, IEEE Control Systems Magazine.

[10]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[11]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[12]  Casimir C. Klimasauskas.  Neural nets tell why , 1991 .

[13]  Robert Hecht-Nielsen,et al.  Theory of the backpropagation neural network , 1989, International 1989 Joint Conference on Neural Networks.