Abstract
In this study, we extend a minimal resource-allocating network (MRAN) which is an on-line learning system for Gaussian radial basis function networks (GRBFs) with growing and pruning strategies so as to realize dimension selection and low computational complexity. We demonstrate that the proposed algorithm outperforms conventional algorithms in terms of both accuracy and computational complexity via some experiments.
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
Lu, Y., Sundararajan, N., Saratchandran, P.: Neural Computation. 9, 461–478 (1997)
Sundararajan, N., Saratchandran, P., Lu, Y.: World Scientific (1999)
Li, Y., Sundararajan, N., Saratchandran, P.: IEE Proc. Control Theory Appl. 147(4), 476–484 (2000)
Poggio, T., Girosi, F.: Proc. IEEE 78(9), 1481–1497 (September 1990)
Puskorius, G.V., Feldkamp, L.A.: Proc. International Joint Conference on Neural Networks. In: Seattle, vol. I, pp. 771–777 (1991)
Iiguni, Y., Sakai, H., Tokumaru, H.: IEEE Trans. Signal Processing. 40(4), 959–966 (April 1992)
Shah, S., Palmieri, F., Datum, M.: Neural Networks. 5(5), 779–787 (1992)
Birgmeier, M.: Proc. 1995 IEEE Int. Conf. Neural Networks., 259–264 (November 1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nishida, K., Yamauchi, K., Omori, T. (2004). An On-Line Learning Algorithm with Dimension Selection Using Minimal Hyper Basis Function Networks. In: Pal, N.R., Kasabov, N., Mudi, R.K., Pal, S., Parui, S.K. (eds) Neural Information Processing. ICONIP 2004. Lecture Notes in Computer Science, vol 3316. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30499-9_77
Download citation
DOI: https://doi.org/10.1007/978-3-540-30499-9_77
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23931-4
Online ISBN: 978-3-540-30499-9
eBook Packages: Springer Book Archive