Abstract
Various methods exist for extracting rules from data for classification purposes. We propose a new method for initializing a neural network used for time series modelling and prediction. We extract binary rules from a real valued time series and encode them into a neural network using an adaptation of KBANN. We test the method on the Lorenz system as well as on real world data in the form of a seismic time series. Results show that the method is successful in extracting and encoding prior knowledge. For the Lorenz system training time was halved and better generalization performance in the form of a lower mean squared error was obtained. Better training time and generalization performance was also obtained for the seismic time series.
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
Lacher, R.C., Hruska, S.I., Kuncicky, D.C. Clarke: Backpropagation learning in expert networks. IEEE Transactions on Neural Networks 3(1) (1992) pp. 62–72
Towell, G.G., Shavlik, J.W.: Knowledge-based artificial neural networks. Artificial Intelligence 70(1,2) (1994) pp. 119–160
Opitz, D., Shavlik, J.W.: Dynamically Adding Symbolically Meaningful Nodes to Knowledge-Based Neural Networks. Knowledge-Based Systems (1996) pp. 301–311
Mendecki, A.J.: Seismic Monitoring in Mines Chapman and Hall, London, UK (1997)
Snyders, S., Omlin, C.W.: What Inductive Bias Gives Good Neural Network Training Performance? International Joint Conference on Neural Networks (2000) pp. 445–450
Ishikawa, M.: Structural Learning and Rule Discovery, in Knowledge-Based Neuro-computing, Cloete, I., Zurada, J.M. (eds) MIT Press, London, England (2000) pp. 153–206
Drossu, R., ObradoviĆ, Z.: Datamining Techniques for Designing Neural Network Time Series Predictors, in Knowledge-Based Neurocomputing, Cloete, I., Zurada, J.M. (eds) MIT Press, London, England (2000) pp. 325–367
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
van Zyl, J., Omlin, C.W. (2001). Knowledge-Based Neural Networks for Modelling Time Series. In: Mira, J., Prieto, A. (eds) Bio-Inspired Applications of Connectionism. IWANN 2001. Lecture Notes in Computer Science, vol 2085. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45723-2_70
Download citation
DOI: https://doi.org/10.1007/3-540-45723-2_70
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42237-2
Online ISBN: 978-3-540-45723-7
eBook Packages: Springer Book Archive