Abstract
We present a technique for function approximation in a partitioned domain. In each of the partitions a form containing a Neural Network is utilized with parameterized boundary conditions. This parameterization renders feasible the parallelization of the computation. Conditions of continuity across the partitions are studied for the function itself and for a number of its derivatives. A comparison is made with traditional methods and the results are reported.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
De Boor C., A practical guide to Splines, Springer-Verlag, New York 1978.
Kincaid D., and Cheney W., Numerical Analysis, Brooks/Cole Publishing Company 1991.
Hornik K., Stinchcombe M., and White H., Neural Networks 2(1989) 359
Cybenko G., Approximation by superpositions of a sigmoidal function, Mathematics of Control Signals and Systems 2(1989) 303–314
Bishop C., Neural Networks for Pattern recognition, Oxford University Press, 1995.
Lagaris I. E., Likas A., Fotiadis D. I., Artificial Neural Networks for solving ordinary and partial differential equations, IEEE Trans. on Neural Networks, 9(1998) 987–1000.
Lagaris I. E., Likas A., Fotiadis D. I., Artificial Neural Network methods in Quantum Mechanics, Computer Physics Communications, 104(1997) 1–14
Lagaris I. E., Likas A., Papageorgiou D. G., Neural Network methods for boundary value problems with irregular boundaries, IEEE Trans. on Neural Networks, 11(2000)1041–1049
Obreshkov N., On the Mechanical Quadratures, J. Bulgar. Acad. Sci. and Arts LXV-8,(1942)191–289
Stochastic Global Optimization Methods: Clustering Methods. A.H.G Rinnooy Kan, G.T. Timmer, Mathematical Prograaming 39(1987) pp:27–56.
Papageorgiou D. G., Demetropoulos I. N. and Lagaris I. E., The Merlin Control Language for strategic optimization, Comput. Phys. Commun. 109(1998)250–275
Papageorgiou D. G., Demetropoulos I. N. and Lagaris I. E., MERLIN-3.0 A multidimensional optimization environment, Comput. Phys. Commun. 109(1998)227–249
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tsoulos, I.G., Lagaris, I.E., Likas, A.C. (2002). Piecewise Neural Networks for Function Approximation, Cast in a Form Suitable for Parallel Computation. In: Vlahavas, I.P., Spyropoulos, C.D. (eds) Methods and Applications of Artificial Intelligence. SETN 2002. Lecture Notes in Computer Science(), vol 2308. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46014-4_28
Download citation
DOI: https://doi.org/10.1007/3-540-46014-4_28
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43472-6
Online ISBN: 978-3-540-46014-5
eBook Packages: Springer Book Archive