Abstract
The Self-Organising Feature Map (SOFM) is one of the unsupervised neural models of most widespread use. Several studies have been carried out in order to determine the degree of topology-preservation for this data projection method, and the influence of the distance measure used, usually Euclidean or Manhattan distance. In this paper, by using a new topology-preserving representation of the SOFM and the well-known Sammon’s stress, graphical and numerical comparisons are shown between both possibilities for the distance measure. Our projection method, based on the relative distances between neighbouring neurons, gives similar information to those of the Sammon projection, but in a graphical way.
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
Kohonen, T. Self-Organization and Associative Memory. Springer-Verlag, 1.989.
Martín del Brío, B. Procesamiento Neuronal con Mapas Auto-organizados: Arquitecturas Digitales. PhD Thesis, University of Zaragoza, Spain, 1.994.
Martín del Brío, B., Medrano Marqués, N. Hernández Sánchez, S. “A Low-Cost Neuroprocessor Board for Emulating the SOFM Neural Model”. Proc. of the 5 th IEEE International Conference on Electronics, Circuits and Systems, ICECS’98, Lisboa, Sept. 1.998.
Villmann, T., Der, R., Hermann, M., Martinetz, T.M. “Topology Preservation in Self-Organizing Feature Maps: Exact Definition and Measurement”, IEEE Transactions on Neural Networks, vol. 8, no 2, pp. 256–266, March, 1.997.
Demartines, P., Hérault, J. “Curvilinear Component Analysis: A Self-Organizing Neural Network for Nonlinear Mapping of Data Sets”. IEEE Trans. on Neural Networks, vol. 8, no 1, pp. 148–154, Jan. 1.997.
Mao, J., Kain, A.J. “Artificial Neural Networks for Feature Extraction and Multivariate Data Projection”. IEEE Transactions on Neural Networks, vol. 6 no 2, pp. 296–317, March, 1.995.
Demartines, P. Analyse de données par réseaux de neurones auto-organisés. PhD Thesis, Institute Nationale Politechnique de Grenoble, 1.994.
Kraaijveld, M.A., Mao, J., Jain, A.K. “A Nonlinear Projection Method Based on Kohonen’s Topology Preserving Maps”. IEEE Transactions on Neural Networks, vol. 6, no 3, pp. 548–559, May, 1.995.
Sammon, J.W. Jr. “A nonlinear mapping for data structure analysis”. IEEE Trans. on Computers, C-18, 5, 401–409, 1.969.
Merz, C.J., Murphy, P.M. UCI Repository of machine learning databases [http://www.ics.uci.edutmlearn/MLRepository.htmlurl] Irvine, CA: Univ. of California, Department of Information and Computer Science, 1.998.
Serrano, C., Martín del Brío, B. “Predicción de la quiebra bancaria mediante el empleo de redes neuronales artificiales”. Revista Española de Financiación y Contabilidad, vol. 22, no 74, pp. 153–176, 1.993.
Medrano Marqués, N. Nuevas Técnicas Hardware y Software para Análisis de Datos con Redes Neuronales. PhD Thesis, University of Zaragoza, Spain, May 1.998.
Martín del Brío, B., Sanz Molina, A. Redes Neuronales y Sistemas Borrosos. Ed. RA-MA. Madrid, 1.997.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Medrano-Marqués, N.J., Martín-del-Brío, B. (1999). Topology preservation in SOFM: An euclidean versus manhattan distance comparison. In: Mira, J., Sánchez-Andrés, J.V. (eds) Foundations and Tools for Neural Modeling. IWANN 1999. Lecture Notes in Computer Science, vol 1606. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0098218
Download citation
DOI: https://doi.org/10.1007/BFb0098218
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66069-9
Online ISBN: 978-3-540-48771-5
eBook Packages: Springer Book Archive