Abstract
Neural networks applied in control loops and safety-critical domains have to meet more requirements than just the overall best function approximation. On the one hand, a small approximation error is required, on the other hand, the smoothness and the monotonicity of selected input-output relations have to be guaranteed. Otherwise the stability of most of the control laws is lost. Three approaches for partially monotonic models are compared in this article, namely Bounded Derivative Network (BDN) [1], Monotonic Multi-Layer Perceptron Network (MONMLP) [2], and Constrained Linear Regression (CLR). Authors investigated the advantages and disadvantages of these approaches related to approximation performance, training of the model and convergence.
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.
References
Turner, P., Guiver, J., Brian, L.: Introducing The State Space Bounded Derivative Network For Commercial Transition Control. In: Proceedings of the American Control Conference, Denver, Colorado, June 4-6 (2003)
Lang, B.: Monotonic Multi-layer Perceptron Networks as Universal Approximators. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) ICANN 2005. LNCS, vol. 3697, pp. 31–37. Springer, Heidelberg (2005)
Zhang, H., Zhang, Z.: Feed forward networks with monotone constraints. In: IEEE International Joint Conference on Neural Networks IJCNN 1999, Washington, DC, USA, vol. 3, pp. 1820–1823 (1999)
Sill, J.: Monotonic Networks, Advances in Neural Information Processing Systems, Cambridge, MA, vol. 10, pp. 661–667 (1998)
Sill, J., Abu-Mostafa, Y.S.: Monotonicity hints, Advances in Neural Information Processing Systems, Cambridge, MA, vol. 9, pp. 634–640 (1997)
Kay, H., Ungar, L.H.: Estimating monotonic functions and their bounds. AIChE J. 46, 2426
Tarca, L.A., Grandjean, B.P.A., Larachi, F.: Embedding monotonicity and concavity information in the training of multiphase flow neural network correlations by means of genetic algorithms. Computers and Chemical Engineering 28(9), 1701–1713 (2004)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Minin, A., Lang, B. (2008). Comparison of Neural Networks Incorporating Partial Monotonicity by Structure. In: Kůrková, V., Neruda, R., Koutník, J. (eds) Artificial Neural Networks - ICANN 2008. ICANN 2008. Lecture Notes in Computer Science, vol 5164. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87559-8_62
Download citation
DOI: https://doi.org/10.1007/978-3-540-87559-8_62
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-87558-1
Online ISBN: 978-3-540-87559-8
eBook Packages: Computer ScienceComputer Science (R0)