Abstract
This work addresses an important problem in Feedforward Neural Networks (FNN) training, i.e. finding the pseudo-global minimum of the cost function, assuring good generalization properties to the trained architecture. Firstly, pseudo-global optimization is achieved by employing a combined parametric updating algorithm which is supported by the transformation of network parameters into interval numbers. It solves the network weight initialization problem, performing an exhaustive search for minimums by means of Interval Arithmetic (IA). Then, the global minimum is obtained once the search has been limited to the region of convergence (ROC). IA allows representing variables and parameters as compact-closed sets, then, a training procedure using interval weights can be done. The methodology developed is exemplified by an approximation of a known non-linear function in last section.
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
Duch, W., Adamczak, R., Jankowski, N.: Initialization and Optimization of Multilayered Perceptrons. In: Proceedings of the 3rd Conference on Neural Networks and Their Applications, Kule, Poland, pp. 105–110 (1997)
Thimm, G., Fiesler, E.: High-Order and Multilayer Perceptron Initialization. IEEE Transactions on Neural Networks 8, 349–359 (1997)
Erdogmus, D., Fontenla-Romero, O., Principe, J., Alonso-Betanzos, A., Castillo, E., Jenssen, R.: Accurate Initialization of Neural Network Weights by Backpropagation of the Desired Response. In: Proceedings of the International Joint Conference on Neural Networks, Portland, USA, vol. 3, pp. 2005–2010 (2003)
Colla, V., Reyneri, L., Sgarbi, M.: Orthogonal Least Squares Algorithm Applied to the Initialization of Multilayer Perceptrons. In: Proceedings of the European Symposium on Artificial Neural Networks, pp. 363–369 (1999)
Yam, Y., Chow, T.: A New Method in Determining the Initial Weights of Feedforward Neural Networks. Neurocomputing 16, 23–32 (1997)
Husken, M., Goerick, C.: Fast Learning for Problem Classes Using Knowledge Based Network Initialization. In: Proceedings of the IJCNN, pp. 619–624 (2000)
Hansen, E.: Global Optimization using Interval Analysis. Marcel Dekker, New York (1992)
Stolfi, J., Figuereido, L.: Self–Validated Numerical Methods and Applications. In: 21st Brazilian Mathematics Colloquium, IMPA (1997)
Jaulin, L., Kiefer, M., Didrit, O., Walter, E.: Applied Interval Analysis. Laboratoire des Signaux et Systèmes, CNRS-SUPÉLEC. Université Paris-Sud, France (2001)
Chen, S., Wu, J.: Interval optimization of dynamic response for structures with interval parameters. Computer and Structures 82, 1–11 (2004)
Valdés, H., Flaus, J.-M., Acuña, G.: Moving horizon state estimation with global convergence using interval techniques: application to biotechnological processes. Journal of Process Control 13, 325–336 (2003)
Cybenko, G.: Approximation by Superposition of a Sigmoidal Function. Mathematics of Control, Signals and Systems 2, 303–314 (1989)
Hornik, K., Stinchcombe, M., White, H.: Multilayer Feedforward Networks are Universal Approximators. Neural Networks 2, 359–366 (1989)
Attali, J., Pagès, G.: Approximations of Functions by a Multilayer Perceptron: a New Approach. Neural Networks 10, 1069–1081 (1997)
Acuña, G., Pinto, E.: Development of a Matlab® Toolbox for the Design of Grey-Box Neural Models. International Journal of Computers, Communications and Control 1, 7–14 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jamett, M., Acuña, G. (2006). An Interval Approach for Weight’s Initialization of Feedforward Neural Networks. In: Gelbukh, A., Reyes-Garcia, C.A. (eds) MICAI 2006: Advances in Artificial Intelligence. MICAI 2006. Lecture Notes in Computer Science(), vol 4293. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11925231_29
Download citation
DOI: https://doi.org/10.1007/11925231_29
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-49026-5
Online ISBN: 978-3-540-49058-6
eBook Packages: Computer ScienceComputer Science (R0)