A Clustering Based Method to Stipulate the Number of Hidden Neurons of mlp Neural Networks: Applications in Pattern Recognition
DOI:
https://doi.org/10.5540/tema.2008.09.02.0351Abstract
In this paper, we propose an algorithm to obtain the number of necessary hidden neurons of single-hidden-layer feed forward networks (SLFNs) for different pattern recognition application tasks. Our approach is based on clustering analysis of the data in each class. We show by simulations that the proposed approach requires less computation CPU time and error rates as well as a smaller number of neurons than other methods.References
[1] A. Asuncion, D.J. Newman, “UCI Machine Learning Repository”, Irvine, CA: University of California, School of Information and Computer Science, 2007. Available: http://www.ics.uci.edu/~mlearn/MLRepository.html
W. Duch, R. Adamczak, N. Jankowski, Initialization and optimization of multilayered perceptrons, in “Proceedings of the 3th Conference on Neural Networks and Their Applications”, pp. 105-110, 1997.
G.B. Huang, H.A. Babri, Upper bounds on the number of hidden neuron in feedforward networks with arbitrary bounded nonlinear activation functions, IEEE Transactions on Neural Networks, 9, No. 1 (1998), 224-229.
R.A. Johnson, D.W. Wichern, “Applied Multivariate Statistical Analysis”, 5th ed., Prentice Hall, Upper Saddle River, 2002.
R.P. Lippmann, Pattern classification using neural networks, IEEE Communications Magazine, (1989), 47-64.
S.A. Mingoti, “An´alise de Dados atrav´es de Metodos de Estat´ıstica Multivariada: uma Abordagem Aplicada”, UFMG, Belo Horizonte, 2005.
H.C. Romesburg, “Cluster Analysis for Researchers”, Robert E. Krieger, Malabar, 1990.
M.R. Silvestre, L.L. Ling, Optimization of neural classifiers based on Bayesian decision boundaries and idle neurons pruning, in “Proceedings of the 16th International Conference on Pattern Recognition”, pp. 387-390, 2002.
N. Weymaere, J.P. Martens, On the initialization and optimization of multilayer perceptrons, IEEE Transactions on Neural Networks, 5, No. 5, (1994), 738-751.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish in this journal agree to the following terms:
Authors retain copyright and grant the journal the right of first publication, with the work simultaneously licensed under the Creative Commons Attribution License that allows the sharing of the work with acknowledgment of authorship and initial publication in this journal.
Authors are authorized to assume additional contracts separately, for non-exclusive distribution of the version of the work published in this journal (eg, publish in an institutional repository or as a book chapter), with acknowledgment of authorship and initial publication in this journal.
Authors are allowed and encouraged to publish and distribute their work online (eg, in institutional repositories or on their personal page) at any point before or during the editorial process, as this can generate productive changes as well as increase impact and the citation of the published work (See The effect of open access).
This is an open access journal which means that all content is freely available without charge to the user or his/her institution. Users are allowed to read, download, copy, distribute, print, search, or link to the full texts of the articles, or use them for any other lawful purpose, without asking prior permission from the publisher or the
author. This is in accordance with the BOAI definition of open access
Intellectual Property
All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License under attribution BY.
