Conventional modeling of the multilayer perceptron using polynomial basis functions

Authors:
M. -S. Chen;M. T. Manry
Affiliations:
Dept. of Electr. Eng., Texas Univ., Arlington, TX;-
Venue:
IEEE Transactions on Neural Networks
Year:
1993

Citing 0
Cited 1

A clustering algorithm for radial basis function neural network initialization

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A technique for modeling the multilayer perceptron (MLP) neural network, in which input and hidden units are represented by polynomial basis functions (PBFs), is presented. The MLP output is expressed as a linear combination of the PBFs and can therefore be expressed as a polynomial function of its inputs. Thus, the MLP is isomorphic to conventional polynomial discriminant classifiers or Volterra filters. The modeling technique was successfully applied to several trained MLP networks