Lale Ozyilmaz
Not Available
Tulay Yildirim
Not Available
Kevser Koklu
Not Available
ABSTRACT
In this work, various neural network algorithms have been compared for function approximation problems. Multilayer Perceptron (MLP) structure with standard back propagation, MLP with fast back propagation (adaptive learning and momentum term added), MLP with Levenberg-Marquardt learning algorithms, Radial Basis Function (RBF) network structure trained by OLS algorithm and Conic Section Function Neural Network (CSFNN) with adaptive learning have been investigated for various functions. Results showed that the neural algorithms can be used for functional estimation as an alternative to classical methods.
PDF References Citation
How to cite this article
Lale Ozyilmaz, Tulay Yildirim and Kevser Koklu, 2002. Comparision of Neural Algorithms for Funchtion Approximation. Journal of Applied Sciences, 2: 288-294.
DOI: 10.3923/jas.2002.288.294
URL: https://scialert.net/abstract/?doi=jas.2002.288.294
DOI: 10.3923/jas.2002.288.294
URL: https://scialert.net/abstract/?doi=jas.2002.288.294
REFERENCES
- Sherif, M.B. and C.G. Atkeson, 1991. Generalization properties of radial basis functions. Proceedings of the Conference on Advances in Neural Information Processing Systems 3, (NIPS`91), Morgan Kaufmann Publishers Inc., San Francisco, CA, USA., pp: 707-713.
Direct Link - Broomhead, D.S. and D. Lowe, 1988. Multivariable functional interpolation and adaptive networks. Complex Syst., 2: 321-355.
Direct Link - Dorffner, G., 1994. Unified framework for mlps and rbfns: Introducing conic section function networks. Cybernetics Syst., 25: 511-554.
CrossRefDirect Link - Geva, S. and J. Sitte, 1992. A constructive method for multivariate function approximation bymultilayer perceptrons. IEEE Trans. Neural Networks, 3: 621-624.
CrossRefDirect Link - Hush, D.R. and B.G. Horne, 1993. Progress in supervised neural networks. IEEE Signal Process. Magazine, 10: 8-39.
CrossRefDirect Link - Lippmann, R., 1987. An introduction to computing with neural nets. IEEE ASSP Mag., 4: 4-22.
CrossRefDirect Link - Poggio, T. and F. Girosi, 1990. Networks for approximation and learning. Proc. IEEE, 78: 1481-1497.
CrossRefDirect Link - Chen, S., C.F.N. Cowan and P.M. Grant, 1991. Orthogonal least squares learning algorithm for radial basis function networks. IEEE Trans. Neural Networks, 2: 302-309.
CrossRefDirect Link