Abstract
We present a hybrid Radial Basis Function (RBF) – sigmoid neural network with a three-step training algorithm that utilises both global search and gradient descent training. We test the effectiveness of our method using four synthetic datasets and demonstrate its use in wave overtopping prediction. It is shown that the hybrid architecture is often superior to architectures containing neurons of a single type in several ways: lower errors are often achievable using fewer hidden neurons and with less need for regularisation. Our Global-Local Artificial Neural Network (GL-ANN) is also seen to compare favourably with both Perceptron Radial Basis Net (PRBFN) and Regression Tree RBFs.
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
Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd edn. Prentice-Hall, Englewood Cliffs (1999)
Moody, J., Darken, C.: Fast learning in networks of locally-tuned processing units. Neural Computation 1, 281–294 (1989)
Cohen, S., Intrator, N.: A Hybrid Projection-based and Radial Basis Function Architecture. Pattern Analysis and Applications 5, 113–120 (2002)
Orr, M.: Introduction to Radial Basis Function Networks (1996), Available from http://www.anc.ed.ac.uk/~mjo/rbf.html
Friedman, J.: Multivariate adaptive regression splines. Annals of Statistics 19, 1–141 (1991)
Mackay, D.: Bayesian Interpolation. Neural Computation 4(3), 415–447 (1992)
Besley, P.: Overtopping of Seawalls: Design and Assessment Manual, Environment Agency R&D Technical Report W178 (1999)
Shiach, J., Mingham, C., Ingram, D., Bruce, T.: The applicability of the shallow water equations for modelling violent wave overtopping. Coastal Engineering 51, 1–15 (2004)
Wedge, D., Ingram, D., Mingham, C., McLean, D., Bandar, Z.: Neural Network Architectures and Overtopping Predictions. Submitted to Maritime Engineering (2004)
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
Wedge, D., Ingram, D., McLean, D., Mingham, C., Bandar, Z. (2005). A Global-Local Artificial Neural Network with Application to Wave Overtopping Prediction. 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_18
Download citation
DOI: https://doi.org/10.1007/11550907_18
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)