Abstract
Functional networks combine both domain and data knowledge to develop optimal network architectures for some types of interesting problems. The topology of the network is obtained from qualitative domain knowledge, and data is used to fit the processing functions appearing in the network; these functions are supposed to be linear combinations of known functions from appropriate families. In this paper we showthat these functions can also be estimated using feedforward neural nets, making no assumption about the families of functions involved in the problem. The resulting models are optimal modular network architectures for the corresponding problems. Several examples from nonlinear time series prediction are used to illustrate the performance of these models when compared with standard functional and neural networks.
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
Hertz, J., Krogh, A. and Palmer, R. G.: Introduction to the Theory of Neural Computation. Addison Wesley, 1991.
Cybenko, G.: Approximation by supperpositions of a sigmoidal function. Mathematics of Control, Signals, and Systems 2, 303–314, 1989.
Wermter, S. and Sun, R. editors: Hybrid Neural Systems. Springer-Verlag (Lecture Notes in Computer Science, Vol. 1778), 2000.
Happel, B. and Murre, J.: Design and evolution of modular neural network architectures. Neural Networks 7, 985–1004, 1994.
Ballard, D.: Modular learning in neural networks. Sixth National Conference on AI 1, 13–17, 1987.
Boers, E. J. W., Kuiper, H., Happel, B. L. M., and Sprinkhuizen-Kuyper, I. G.: Designing modular artificial neural networks. In H. A. Wijshoff, editor: Proceedings of Computing Science in The Netherlands, 87–96, 1993.
Castillo, E., Cobo, A., Gutiérrez, J. M. and Pruneda, E.: An Introduction to Functional Networks with Applications. Kluwer Academic Publishers, 1999.
Aczél, J.: Lectures on Functional Equations and Their Applications. Academic Press, 1966.
Castillo. E.: Functional networks. Neural Processing Letters 7, 151–159, 1998.
Castillo, E. and Gutiérrez, J. M.: A minimax method for learning functional networks. Neural Processing Letters 11, 39–49, 2000.
Castillo, E., Gutiérrez, J. M., Hadi, A. S. and Lacruz, B.: Some applications of functional networks in statistics and engineering. Technometrics 43, 10–24, 2001.
Stern, H. S.: Neural networks in applied statistics. Technometrics 38, 205–214, 1993.
Misiurewicz, M.: The Lozi map has a strange attractor. In R. Hellemann, editor: Nonlinear Dynamics, Annals of the NY Academy of Science 357, 348–358, 1980.
Castillo, E. and Gutiérrez, J. M.: Nonlinear time series modeling and prediction using functional networks. Physics Letters A 244, 71–84, 1998.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cofiño, A.S., Gutiérrez, J.M. (2001). Optimal Modular Feedfroward Neural Nets Based on Functional Network Architectures. In: Mira, J., Prieto, A. (eds) Connectionist Models of Neurons, Learning Processes, and Artificial Intelligence. IWANN 2001. Lecture Notes in Computer Science, vol 2084. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45720-8_35
Download citation
DOI: https://doi.org/10.1007/3-540-45720-8_35
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42235-8
Online ISBN: 978-3-540-45720-6
eBook Packages: Springer Book Archive