Abstract
An Interval Arithmetic Perceptron (IAP) is a neural network where the usual perceptron topology uses the intervals as numerical representation of internal parameters and output: in this paper we present the learning of such a network and show its performance in weight pruning and in the consequent identification of the importance of input features. The applications to the Iris and the Breast Cancer database are presented and simple and efficient classification rules are obtained. IAP compares favourably with a well-established feature screening method.
This is a preview of subscription content, log in via an institution to check access.
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
Anguita D. et al., Incorporating a priori knowledge into neural networks, Electronic Letters, Vol.31, no.22, october 1995.
G.P.Drago, S.Ridella, Statistically Controlled Activation Weight Initialization, IEEE Transactions on Neural Networks, Vol.3, NO. 4, July 1992.
Drago G.P. and Ridella S., An Adaptive Momentum Back Propagation (AMBP), Neural Computing Applications, no. 3, 1995, pp. 213–221.
Drago G.P. and Ridella S., Pruning with Interval Arithmetic Perceptron (IAP), Internal Report ICE, no.7, 1996.
Ishibuchi H. and Tanaka H., An architecture jof neural networks with interval weights and its application to fuzzy regression analysis, Fuzzy sets andd Systems, 57, 1993, pp. 27–39.
Steppe J.M. and Bauer K.W., Improved feature screening in feedforward neural networks, Neurocomputing, 13, 1996, pp. 47–58.
Vapnik V.N., The Nature of Statistical Learning Theory, New York: Springer-Verlag, 1995.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag London Limited
About this paper
Cite this paper
Drago, G.P., Ridella, S. (1998). Interval Arithmetic Perceptron with pruning capability. In: Marinaro, M., Tagliaferri, R. (eds) Neural Nets WIRN VIETRI-97. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-1520-5_31
Download citation
DOI: https://doi.org/10.1007/978-1-4471-1520-5_31
Publisher Name: Springer, London
Print ISBN: 978-1-4471-1522-9
Online ISBN: 978-1-4471-1520-5
eBook Packages: Springer Book Archive