Share Email Print
cover

Proceedings Paper

Stretch and hammer neural networks
Author(s): Steven C. Gustafson; Gordon R. Little; Mark August Manzardo; Todd Steven Puterbaugh
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Stretch and hammer neural networks use radial basis function methods to achieve advantages in generalizing training examples. These advantages include (1) exact learning, (2) maximally smooth modeling of Gaussian deviations from linear relationships, (3) identical outputs for arbitrary linear combination of inputs, and (4) training without adjustable parameters in a predeterminable number of steps. Stretch and hammer neural networks are feedforward architectures that have separate hidden neuron layers for stretching and hammering in accordance with an easily visualized physical model. Training consists of (1) transforming the inputs to principal component coordinates, (2) finding the least squares hyperplane through the training points, (3) finding the Gaussian radial basis function variances at the column diagonal dominance limit, and (4) finding the Gaussian radial basis function coefficients. The Gaussian radial basis function variances are chosen to be as large as possible consistent with maintaining diagonal dominance for the simultaneous linear equations that must be solved to obtain the basis function coefficients. This choice insures that training example generalization is maximally smooth consistent with unique training in a predeterminable number of steps. Stretch and hammer neural networks have been used successfully in several practical applications.

Paper Details

Date Published: 1 July 1992
PDF: 10 pages
Proc. SPIE 1710, Science of Artificial Neural Networks, (1 July 1992); doi: 10.1117/12.140137
Show Author Affiliations
Steven C. Gustafson, Univ. of Dayton Research Institute (United States)
Gordon R. Little, Univ. of Dayton Research Institute (United States)
Mark August Manzardo, Univ. of Dayton Research Institute (United States)
Todd Steven Puterbaugh, Univ. of Dayton Research Institute (United States)


Published in SPIE Proceedings Vol. 1710:
Science of Artificial Neural Networks
Dennis W. Ruck, Editor(s)

© SPIE. Terms of Use
Back to Top