Abstract
Multi-layer perceptron networks as universal approximators are well-known methods for system identification. For many applications a multi-dimensional mathematical model has to guarantee the monotonicity with respect to one or more inputs. We introduce the MONMLP which fulfils the requirements of monotonicity regarding one or more inputs by constraints in the signs of the weights of the multi-layer perceptron network. The monotonicity of the MONMLP does not depend on the quality of the training because it is guaranteed by its structure. Moreover, it is shown that in spite of its constraints in signs the MONMLP is a universal approximator. As an example for model predictive control we present an application in the steel industry.
An erratum to this chapter can be found at http://dx.doi.org/10.1007/11550907_163 .
This is a preview of subscription content, log in via an institution to check access.
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
Abu-Mostafa, Y.S.: Hints. Neural Computation 7, 639–671 (1995)
Lampinen, J., Selonen, A.: Multilayer perceptron training with inaccurate derivative information. In: Proc. IEEE International Conference on Neural Networks ICNN 1995, Perth, West Australia, vol. 5, pp. 2811–2815 (1995)
Sill, J., Abu-Mostafa, Y.S.: Monotonicity hints. In: Advances in Neural Information Processing Systems, Cambridge, MA, vol. 9, pp. 634–640 (1997)
Sill, J.: Monotonic networks. In: Advances in Neural Information Processing Systems, Cambridge, MA, vol. 10, pp. 661–667 (1998)
Rollfinke, R.: Globale Modellierung mit Neuronalen Netzen unter Einhaltung von Nebenbedingungen in den Gradienten. Diploma thesis in cooperation with Siemens AG, Fakultät für Informatik und Automatisierung, TU Ilmenau, Germany (2000)
Lang, B.: Können Neuronale Netze monotones Verhalten für bestimmte Dimensionen garantieren? Technical report, Siemens AG, unpublished, Munich, Germany (1999)
Zhang, H., Zhang, Z.: Feedforward networks with monotone constraints. In: Proc. IEEE International Joint Conference on Neural Networks IJCNN 1999, Washington, DC, USA, vol. 3, pp. 1820–1823 (1999)
Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Networks 2, 359–366 (1989)
Löffler, H.U., Döll, R., Forsch, G.: Microstructure monitor controls product quality at Thyssen Beeckerwerth. In: Proc. METEC Congress, 3rd European Rolling Conference, Düsseldorf, Germany, pp. 221–225 (2003)
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
Lang, B. (2005). Monotonic Multi-layer Perceptron Networks as Universal Approximators. 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_6
Download citation
DOI: https://doi.org/10.1007/11550907_6
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)