Abstract
In this work, a new supervised learning method for single layer neural networks based on a regularized cost function is presented. This method obtains the optimal weights and biases by solving a system of linear equations and therefore it is always guaranteed the global optimum solution. In order to verify the soundness of the proposed learning algorithm and to analyze the effect of the regularization term, two simulations, one for a classification problem and another for a regression problem, were performed. The obtained results demonstrated the validity of the method.
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
Girosi, F., Jones, M., Poggio, T.: Regularization theory and neural networks architectures. Neural Computation 7 (1995) 219–269
Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, New York (1995)
Hinton, G.E.: Learning translation invariant recognition in massively parallel networks. In Nijman, A.J., de Bakker, J., Treleaven, P.C., eds.: PARLE Conference on Parallel Architectures and Languages Europe, Berlin, Springer-Verlag (1987) 1–13
Fontenla-Romero, O., Erdogmus, D., Principe, J.C., Alonso-Betanzos, A., Castillo, E.: Accelerating the convergence speed of neural networks learning methods using least squares. In: 11th European Symposium on Artificial Neural Networks (ESANN). (2003) (in press)
Box, G.E.P., Jenkins, G.M.: Time series analysis, forecasting and control. Holden Day, San Francisco (1970)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Suárez-Romero, J.A., Fontenla-Romero, O., Guijarro-Berdiñas, B., Alonso-Betanzos, A. (2003). A new learning method for single layer neural networks based on a regularized cost function. In: Mira, J., Álvarez, J.R. (eds) Computational Methods in Neural Modeling. IWANN 2003. Lecture Notes in Computer Science, vol 2686. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44868-3_35
Download citation
DOI: https://doi.org/10.1007/3-540-44868-3_35
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40210-7
Online ISBN: 978-3-540-44868-6
eBook Packages: Springer Book Archive