Abstract
In this paper we present a scheme of classification based on a particular processing element (“neuron”) called Yprel. The main characteristics of the approach are: (i) an Yprel classifier is a set of Yprels networks, each network being associated with a particular class; (ii) the learning is supervised and conducted class by class; (iii) the structure of the network is not a priori chosen, but is determined step by step during the learning process; (iv) the learning process is incremental: each network improves its own learning base with the errors of the previous test; (v) networks cooperate: each network can use the outputs of the previously builded networks. Preliminary results are given on a well-known classification task (recognition of typographic characters).
Preview
Unable to display preview. Download preview PDF.
References
BALLARD A. H., BROWN C.M., Computer vision. Prentice-Hall, 1982.
BELAID A, BELAID Y., Reconnaissance des formes, InterEditions, 1992.
BREIMAN L., FRIEDMAN J.H., OLSHEN R.A., STONE C.J., Classification and Regression Trees, Wadsworth&Brooks, Pacific Grove, CA, 1984.
FAHLMAN, S.E., LEBIERE, C., The Cascade-correlation learning architecture, Advances in Neural Information Processing Systems, D.S. Touretsky Ed., 2, 524–532, Morgan Kauffmann, 1990.
FOGELMAN-SOULIE, F., ROBERT, Y., TCHUENTEE, M. Automata Networks in Computer Science. Manchester Univ. Press, 1987.
FREAN, M. The Upstart algorithm: a method for constructing and training feed-forward neural networks, Neural Computation, 2, 198–209, 1990.
GENTRIC P., WITHAGEN H., Constructive Methods for a new Classifier Based on a Radial-basis-function Neural Network accelerated by a Tree, New Trends in Neural Computation, J. Mira, J. Cabestani, A. Prieto Eds., 125–130, Springer-Verlag, Berlin, 1993.
R. HECHT-NIELSEN, Neurocomputing, Addison-Wesley, Reading, MA, 1990.
H. HÜNING, A node Splitting Algorithm that reduces the Number of Connections in a Hamming Distance Classifying Network, New Trends in Neural Computation, J. Mira, J. Cabestani, A. Prieto Eds., 102–107, Springer-Verlag, Berlin, 1993.
Y. IDAN, J.M. AUGER, N. DARBEL, M. SALES, R. CHEVALLIER, B. DORIZZI, G. CAZUGUEL, Comparative study of neural networks and non parametric statistical methods for off-line handwritten character recognition. Proceedings ICANN 92, Brighton, September 1992.
KAMP, Y., HASLER, M. Réseaux de neurones récursifs pour mémoires associatives. Presses Polytechniques Romandes, Lausanne, 1990.
KOHONEN, T. Self organisation and Associative Memory. Springer series in Information Sciences, Springer Verlag, Berlin, 1988.
LECOURTIER Y., DORIZZI B., SEBIRE P., ENNAJI A., MLP Modular versus Yprel Classifiers, New Trends in Neural Computation, J. Mira, J. Cabestani, A. Prieto Eds., 569–574, Springer-Verlag, Berlin, 1993.
Y. LECOURTIER, A. ENNAJI, F. GILLES, P. CHAVY, Yprel networks and classification. IEEE SMC Conf, 3, 463–468, Le TOUQUET 1993.
Y. LECOURTIER, A. ENNAJI, E. STOCKER, F. GILLES, Réseaux d'Yprels, classification et apprentissage incrémental. Actes du 3ème colloque CNED, 109–118, Rouen 1994.
G. L. Martin, J. A. Pittman, Recognizing hand printed letters and digits using backpropagation learning, Neural Computation 3, 258–267, 1991.
PEREZ J.C., VIDAL E., Constructive Design of LVQ and DSM Classifiers, New Trends in Neural Computation, J. Mira, J. Cabestani, A. Prieto Eds., 334–339, Springer-Verlag, Berlin, 1993.
RUMELHART, J., Mc CLELLAND, J. Parallel Distributed Processing, MIT Press, Cambridge MA, 1986.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Stocker, E., Lecourtier, Y., Ennaji, A. (1995). A distributed classifier based on Yprel networks cooperation. In: Mira, J., Sandoval, F. (eds) From Natural to Artificial Neural Computation. IWANN 1995. Lecture Notes in Computer Science, vol 930. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-59497-3_193
Download citation
DOI: https://doi.org/10.1007/3-540-59497-3_193
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-59497-0
Online ISBN: 978-3-540-49288-7
eBook Packages: Springer Book Archive