Share Email Print
cover

Proceedings Paper

Roughness/error trade-offs in neural network time series models
Author(s): Steven C. Gustafson; Gordon R. Little; John S. Loomis; Theresa A. Tuthill
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Radial basis function neural network models of a time series may be developed or trained using samples from the series. Each model is a continuous curve that can be used to represent the series or predict future vales. Model development requires a tradeoff between a measure of roughness of the curve and a measure of its error relative to the samples. For roughness defined as the root integrated squared second derivative and for error defined as the root sum squared deviation (which are among the most common definitions), an optimal tradeoff conjecture is proposed and illustrated. The conjecture states that the curve that minimizes roughness subject to given error is a weighted mean of the least squares line and the natural cubic spline through the samples.

Paper Details

Date Published: 4 April 1997
PDF: 4 pages
Proc. SPIE 3077, Applications and Science of Artificial Neural Networks III, (4 April 1997); doi: 10.1117/12.271469
Show Author Affiliations
Steven C. Gustafson, Univ. of Dayton (United States)
Gordon R. Little, Univ. of Dayton (United States)
John S. Loomis, Univ. of Dayton (United States)
Theresa A. Tuthill, Univ. of Dayton (United States)


Published in SPIE Proceedings Vol. 3077:
Applications and Science of Artificial Neural Networks III
Steven K. Rogers, Editor(s)

© SPIE. Terms of Use
Back to Top