Abstract
We study incremental algorithms operating on one- and two-hidden-layer neural networks with linear output units in such way that in each iteration, some new hidden units are put in the first or in the second hidden layer. The weight parameters of the new units are determined and output weights of all units are recalculated. We apply the algorithms to the special class of functions (for predictions of geomagnetic storms).1
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
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
Andrejkovâ, G., Azorovâ, J., Kudela, K.: Artificial neural networks in prediction of D5t Index. Proceedings of the 1-th Slovak Neural Networks Symposium, Vol. II, Herlany, 1996, 51–59
Barron, A. R. (1993) Universal approximation bounds for superposition of sigmoidal function. IEEE Transactions on Information Theory 39, 930–945
Beliczynski, B. (1996): An almost analytical design of incremental discrete functions approximation by one-hidden-layer neural networks. In Proceedings of WCNN’96, 988–991, Lawrence Erlbaum, San Diego.
Jones, L. K. (1992) A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training. Annual of Statistics, 20, 608–613
Knrkovâ, V. (1995) Approximation of Functions by Perceptron Networks with Bounded Number of Hidden Units, Neural Networks, Vol. 8, No. 5, 745–750
Knrkovâ, V., Beliczynski, B. (1995) Incremental approximation by one-hiddenlayer neural networks. In proceedings of ICANN’95, pp. I.505–510, Paris: EC2und Cie.
Knrkovâ, V. (1998) Incremental approximation by neural networks. In Complexity: Neural Network Approach. Eds. K. Warwick, M. Kârny, V. Knrkovâ, Springer, 177–188.
Knrkovâ, V. (2000) Incremental Approximation by Neural Networks, Proceedings of NC’2000, Berlin, p. 12.
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
Andrejková, G. (2000). Incremental Approximation by Layer Neural Networks. In: Sinčák, P., Vaščák, J., Kvasnička, V., Mesiar, R. (eds) The State of the Art in Computational Intelligence. Advances in Soft Computing, vol 5. Physica, Heidelberg. https://doi.org/10.1007/978-3-7908-1844-4_3
Download citation
DOI: https://doi.org/10.1007/978-3-7908-1844-4_3
Publisher Name: Physica, Heidelberg
Print ISBN: 978-3-7908-1322-7
Online ISBN: 978-3-7908-1844-4
eBook Packages: Springer Book Archive