Abstract
Several regularization terms, some of them widely applied to neural networks, such as weight decay and weight elimination, and some others new, are tested when applied to networks with a small number of connections handling continuous variables. These networks are found when using additive algorithms that work by adding processors. First the different methods and their rationale is presented. Then, results are shown, first for curve fitting problems. Since the network constructive algorithm is being used for system modeling, results are also shown for a toy problem that includes recurrency buildup, in order to test the influence of the regularization terms in this process. The results show that this terms can be of help in order to detect unnecessary connections. No clear winner has been found among the presented terms in these tests.
Preview
Unable to display preview. Download preview PDF.
References
Crespo, J.L. “Procesamiento paralelo y distribuido aplicado a la simulación de sistemas”. Ph.D. Thesis, Universidad de Cantabria, Santander (1992)
Hinton, G.E.. “Learning Distributed Representations of Concepts”. Proceedings of the Eighth Annual Conference of the Cognitive Science Society (Amherst 1986), 1–12. Hillsdale: Erlbaum.(1986)
Movellan, J.R. “Error functions to improve noise resistance and generalization in backpropagation networks”. (1989)
Weigend, A.S.; Rumelhart, D.E. y Huberman, B.A., “Generalization by Weight-Elimination with Application to Forecasting”. Advances in Neural Information Processing 3. ed.: R.P. Lippmann, J. Moody and D.S. Touretzky. Morgan Kaufmann, San Mateo, CA.(1991)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Crespo, J.L., Mora, E. (1993). Tests of different regularization terms in small networks. In: Mira, J., Cabestany, J., Prieto, A. (eds) New Trends in Neural Computation. IWANN 1993. Lecture Notes in Computer Science, vol 686. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-56798-4_161
Download citation
DOI: https://doi.org/10.1007/3-540-56798-4_161
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-56798-1
Online ISBN: 978-3-540-47741-9
eBook Packages: Springer Book Archive