Abstract
In this paper, a modeling method of high dimensional piecewise affine models is proposed. Because the model interpolates the outputs at the orthogonal grid points in the input space, the shape of the piecewise affine model is easily understood. The interpolation is realized by a RBFN, whose function is defined with max-min functions. By increasing the number of RBFs, the capability to express nonlinearity can be improved. In this paper, an algorithm to determine the number and locations of RBFs is proposed.
An erratum to this chapter can be found at http://dx.doi.org/10.1007/11550907_163 .
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
Hush, R.D., Horne, B.: Efficient Algorithms for Function Approximation with Piecewise Linear Sigmoidal Networks. IEEE Trans. Neural Networks 9(6), 1129–1141 (1998)
Kahlert, C., Chua, C.O.: A generalized canonical piecewise linear representation. IEEE Trans. Cirsuit Syst. 37, 373–382 (1990)
Kahlert, C., Chua, C.O.: The complete canonical piecewise linear representation-Part 1 The geometry of the domain space. IEEE Trans. Cirsuit Syst. 39, 222–236 (1992)
Ferrari-Trecate, G., Muselli, M., Liberati, D., Morari, M.: A Comparison of Piecewise-Linear Model Descriptions. ACC Arlilgton 5, 3521–3526 (2001)
Estevez, P.A.: Max-Min Propagation Neural Networks: Representation Capabilities, Learning Algorithms and Evolutionary Structuring. Dr thesis of Tokyo University
Kevenaar, T.A.M., Leenaerts, D.M.W.: A Comparison of Piecewise-Linear Model Descriptions. IEEE Trans. Cirsuit Syst. 39(12), 222–236 (1992)
Hashimoto, Y., et al.: Piecewise linear controller improving its own reliability. Journal of process control 6, 129–136 (1996)
Bemporad, A., Morari, M.: Control of systems integrating logic, dynamics, and constraints. Automatica 35, 407–427 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sakamoto, M., Duo, D., Hashimoto, Y., Itoh, T. (2005). Nonlinear Regression with Piecewise Affine Models Based on RBFN. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds) Artificial Neural Networks: Formal Models and Their Applications – ICANN 2005. ICANN 2005. Lecture Notes in Computer Science, vol 3697. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11550907_14
Download citation
DOI: https://doi.org/10.1007/11550907_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28755-1
Online ISBN: 978-3-540-28756-8
eBook Packages: Computer ScienceComputer Science (R0)