Abstract
Neural networks, as a new computational technique, require a comparison of performances to classical techniques. This fundamental research thought appears complicated when it applies to real problems. In this paper, we outline the behaviour of three different algorithms to a common problem of data analysis: the Kohonen self-organization, the classical Principal Component Analysis and the Generalized Hebbian Algorithm. Then, we attempt to give a qualitative comparison of the results and we discuss the difficulty to correctly achieve this step.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
6-References
Baumann, T., Germond, A., Tschudi, D. (1991), Impulse test fault diagnosis on power transformers using Kohonen's self-organizing neural network, Proc. of the Third Symp. on Expert System Applications to power systems, Tokyo & Kobe, April 1991
Bouroche, J.M., Saporta, G., (1987), L'analyse de données, Coll. Que sais-je ?, Presses Universitaires de France, 3ème Edition.
Cherkassky, V., Lari-Najafi, H. (1990), Self-organizing neural network for non-parametric regression analysis, Int. Neural Network Conf, 1, pp. 370–374, Paris
Cottrell, M., Fort, J.C., (1987), Etude d'un processus d'auto-organisation. Annales de l'Institut Henri Poincaré, 23, 1, pp. 1–20
Jutten, C., Guérin, A., Nguyen Thi, H.L., (1991), Adaptive optimization of neural algorithms, to appear in International Workshop on Artificial Neural Networks, Grenada, Spain.
Kohonen, T. (1982), Self-organized formation of topologically correct feature maps. Biol. Cyb. 43, 59–69
Oja, E., (1982), A simplified neuron model as a principal component analyzer. Journal of mathematical biology 15, 267–273
Pontier, J., Dufour, A-B., Normand, M., (1990), Le modèle euclidien en analyses de données, Editions Ellipses, Paris.
Ritter, H. Schulten, K, (1988), “Kohonen's self-organizing maps: exploring their computational capabilities”, Proc. of the Int. Joint Conf. on Neural Networks, pp.I–109, 1–116
Sanger, A., (1989), Optimal unsupervised learning in a single layer linear feedforward neural network, Neural Networks 2, 459–473
Windser, C., Harker, A., (1990), Multi-variate financial index prediction — A neural network study, Int. Neural Network Conf, 1, pp. 357–360, Paris
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Blayo, F., Demartines, P. (1991). Data analysis: How to compare Kohonen neural networks to other techniques?. In: Prieto, A. (eds) Artificial Neural Networks. IWANN 1991. Lecture Notes in Computer Science, vol 540. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0035929
Download citation
DOI: https://doi.org/10.1007/BFb0035929
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-54537-8
Online ISBN: 978-3-540-38460-1
eBook Packages: Springer Book Archive