Abstract
An n-class problem is decomposed into n two-class problems. Naturally, modular multilayer perceptrons (MLPs) come into being. A single- output MLP is behalf of a class and trained by a two-class learning subset. A training subset only consists of all samples from a special class and a part samples from the nearest classes. If the decision boundary of a single-output MLP is open, its outputs are amended by a correction coefficient. This paper clarifies such a fact that the generalization of a single-output MLP is seriously affected by the sample disequilibrium situation. Therefore, the samples from the little class have to be multiplied an enlarging factor. The result of letter recognition shows that the above methods are effective.
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
Setiono, R.: Feedforward neural network construction using cross-validation. Neural Computation 13, 2865–2877 (2001)
Blake, C.L., Merz, C.J.: UCI Repository of machine learning databases, Irvine, CA (1998), http://www.ics.uci.edu/~mlearn/MLRepository.html
Gormann, R.P., et al.: Analysis of hidden units in a layered network trained to classify sonar targets. Neural Networks 1, 75–89 (1988)
Cho, S.B.: Neural-network classifiers for recognizing totally unconstrained handwritten numerals. IEEE Transactions on Neural Networks 8(1), 43–52 (1997)
Daqi, G., Genxing, Y.: Influences of variable scales and activation functions on the performances of multilayer feedforward neural networks. Pattern Recognition 36(4), 869–878 (2003)
Williamson, J.R.: Gaussian ARTMAP: a neural network for fast incremental learning of noisy multidimensional maps. Neural Networks 9(5), 881–897 (1996)
Frey, P.W., Slate, D.J.: Letter recognition using Holland-style adaptive classifiers. Machine Learning 6, 161–182 (1991)
Fogarty, T.: First nearest neighbor classification on Frey and Slate’s letter recognition problem. Machine Learning 9, 387–388 (1992)
Bressan, M., Guillamet, D., Vitria, J.: Using an ICA representation of high dimensional data for object recognition and classification. In: IEEE Conference on CVPR, HI, USA, vol. 1, pp. 1004–1009 (2001)
Islam, M.M., Murase, K.: A new algorithm to design compact two-hidden-layer artificial neural networks. Neural Networks 14, 1265–1274 (2001)
Anand, R., Mehrotra, K.G., Mohan, C.K., et al.: Efficient classification for multiclass problems using modular neural networks. IEEE Transactions on Neural Networks 6(1), 117–124 (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Daqi, G., Zhu, S., Gu, W. (2005). A Modular Single-Hidden-Layer Perceptron for Letter Recognition. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds) Artificial Neural Networks: Biological Inspirations – ICANN 2005. ICANN 2005. Lecture Notes in Computer Science, vol 3696. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11550822_72
Download citation
DOI: https://doi.org/10.1007/11550822_72
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28752-0
Online ISBN: 978-3-540-28754-4
eBook Packages: Computer ScienceComputer Science (R0)