Abstract
We present an ensemble averaging effect for improving the generalization capability of self-generating neural networks applied to classification problems. The results of our computational experiments show that ensemble averaging effect is 1–7% improvements in accuracy comparing with single SGNN for three benchmark problems.
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
Wen, W. X., Pang, V. and Jennings, A.: Self-Generating vs. Self-Organizing, What’s Different? In: Simpson, P. K. (eds.): Neural Networks Theory, Technology, and Applications. IEEE, New York (1996) 210–214
Kohonen, T.: Self-Organizing Maps. Springer-Verlag, Berlin (1995)
Wen, W. X., Jennings, A. and Liu, H.: Learning a Neural Tree. In: International Joint Conf. on Neural Networks. Beijing (1992) 751–756
Inoue, H. and Narihisa, H.: Performance of Self-Generating Neural Network Applied to Pattern Recognition. In: 5th International Conf. on Information Systems Analysis and Synthesis, Vol. 5. Orlando, FL (1999) 608–614
Rumelhart, D., Hinton, G. E. and Williams, R. J.: Learning Internal Representations by Error Propagation. In: Rumelhart, D., McClelland, J. and the PDP Reserch Group (eds.): Parallel Distributed Processing: Explorations in the Microstructure of Cognition. MIT Press, Cambridge, MA (1986) 318–362
Thrun, S. B. et alt: The MONK’s Problems — A Performance Comparison of Different Learning Algorithms. Technical report CMU-CS-91-197. Carnegie Mellon University (1991)
Prehelt, L.: PROBEN1 — A Set of Neural Network Benchmark Problems and Benchmarking Rules. Technical report 21/94. Universität Karlsruhe (1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Inoue, H., Narihisa, H. (2000). Improving Generalization Ability of Self-Generating Neural Networks Through Ensemble Averaging. In: Terano, T., Liu, H., Chen, A.L.P. (eds) Knowledge Discovery and Data Mining. Current Issues and New Applications. PAKDD 2000. Lecture Notes in Computer Science(), vol 1805. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45571-X_22
Download citation
DOI: https://doi.org/10.1007/3-540-45571-X_22
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67382-8
Online ISBN: 978-3-540-45571-4
eBook Packages: Springer Book Archive