Title :
Volterra characterization of neural networks
Author :
Hakim, N.Z. ; Kaufman, J.J. ; Cerf, G. ; Meadows, H.E.
Author_Institution :
Dept. of Electr. Eng., Columbia Univ., New York, NY, USA
Abstract :
The authors analyze the application of the Volterra theory of nonlinear systems to neural networks. Expressions for efficiently computing the Volterra kernels of both a single hidden layer feedforward neural network and a recurrent one are presented. The authors also address the issue of functional representation of the recurrent neural network architecture and delineate a class of systems that can be approximated by this model. Computer simulations are also presented which indicate that neural networks characterization by their Volterra expansion may be useful in optimal architecture selection and assessment of learning and generalization
Keywords :
neural nets; nonlinear systems; Volterra expansion; Volterra kernels; Volterra theory; characterization; class of systems; functional representation; generalisation assessment; learning assessment; network architecture; nonlinear systems; optimal architecture selection; recurrent neural network; single hidden layer feedforward neural network; Computer architecture; Computer networks; Convergence; Feedforward neural networks; Kernel; Neural networks; Nonlinear systems; Orthopedic surgery; Power system modeling; Recurrent neural networks;
Conference_Titel :
Signals, Systems and Computers, 1991. 1991 Conference Record of the Twenty-Fifth Asilomar Conference on
Conference_Location :
Pacific Grove, CA
Print_ISBN :
0-8186-2470-1
DOI :
10.1109/ACSSC.1991.186623