Abstract
Polynomial networks have proven to be useful for solving both classification and estimation problems. Object-oriented software design provides the means to implement a variety of network paradigms in a natural and efficient way. This paper describes the use of object-oriented techniques in network synthesis software development, and the design of a polynomial network classifier. Key design issues such as synthesis algorithms, performance criteria, and regression techniques are addressed in this implementation. To demonstrate the applicability of these techniques, prototype classification software has been developed and used in conjunction with a commercial network estimation package to solve a simple engine response problem. We then apply the software, incorporate the solution into a simulation, and assess the quality of the results.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Barron, A.R. and R.L. Barron, “Statistical Learning Networks: A Unifying View,” Computing Science and Statistics: 1988 Proceedings of the 20th Symposium on the Interface, p. 192–203, 1988.
Barron, A.R., “Predicted Squared Error: A Criterion for Automatic Model Selection,” Self-Organizing Methods in Modeling: GMDH Type Algorithms, edited by S J. Farlow, Marcel-Dekker, Inc., New York, 1984.
Barron, R.L., R.L. Cellucci, P.R. Jordan, III, N.E. Beam, P. Hess, A.R. Barron, “Applications of Polynomial Neural Networks to FDIE and Reconfigurable Flight Control,” Proceedings of the IEEE’ 90 National Aerospace and Electronics Conference (NAECON’ 90). 1990 (NAECON Best Papar Award).
Hess, P., D.W. Abbott, and K.E. Cascone, Multidimensional Search and Optimization: the OMNIsearch algorithm. Internal Report, Barron Associates, Inc. July 1988.
Hess, P. and G.J. Montgomery, “Abduction: Theory and Application,” proceedings of the 4th Annual Aerospace Applications of Artificial Intelligence Conference ( AAAIC). October 1988.
Miller, G.A., “The Magic Number Seven, Plus or Minus Two: Some Limits on our Capacity for Processing Information,” The Psychological Review. March 1956.
Montgomery, GJ, et al., Abduction and Abductory Induction Applied to Strategic Defense Battle Management. Phase I Final Report, AbTech Corporation and Barron Associates, Inc., for U.S. Army Strategic Defense Command, Contract No. DASG60-89-C-0059, 1989.
Press, W., B. Flannery, et al., Numerical Recipes. The Art of Scientific Computing. Cambridge University Press, 1986.
Rummelhart, D., J. McClelland, et al., Parallel Distributed Processing. Massachusetts Institute of Technology, 1986.
Shrier, S., R.L. Barron, and L.O. Gilstrap, “Polynomial and Neural Networks: Analogies and Engineering Applications,” proceedings of the IEEE First Annual International Conference on Neural Networks. IEEE Press, 1987.
Söderström, T., and P. Stoica, Chapter 9, System Identification. Prentice Hall International (UK) Ltd, 1989.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer-Verlag New York, Inc.
About this paper
Cite this paper
Cellucci, R.L., Hess, P. (1992). Techniques for Developing and Applying Polynomial Network Synthesis Software. In: Page, C., LePage, R. (eds) Computing Science and Statistics. Springer, New York, NY. https://doi.org/10.1007/978-1-4612-2856-1_26
Download citation
DOI: https://doi.org/10.1007/978-1-4612-2856-1_26
Publisher Name: Springer, New York, NY
Print ISBN: 978-0-387-97719-5
Online ISBN: 978-1-4612-2856-1
eBook Packages: Springer Book Archive