Abstract
Self-organizing maps (SOM) have been obtained mainly on regular lattices, embedded in euclidean or non-euclidean spaces [1]. We present preliminar results that show SOM can be formed on non-regular lattices by giving evidence that topographic error (TE) is influenced by a few statistical parameters of the neuron lattice, such as the characteristic path length (L), the cluster coefficient (C) and the characteristic connectivity length (Lg). TE is lower not in regular lattices, but in lattices that present a particular set of statistical parameters. In an attempt to identify that set of statistical parameters, we applied mutual information function between the parameters and the TE as well as C4.5 algorithm to obtain rules that identify lattices in which SOMs show low TE.
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
Ritter, H.: Self-Organizing Maps on non-euclidean Spaces Kohonen Maps. In: Oja, E., Kaski, S. (eds.), pp. 97–108 (1999)
Cottrell, M., Fort, J.C., Pagés, G.: Theoretical aspects of the SOM algorithm. Neurocomputing 21, 119–138 (1998)
Kirk, J., Zurada, J.: A two-stage algorithm for improved topography preservation in self-organizing maps. Int. Con. on Sys., Man and Cyb. 4, 2527–2532 (2000)
Haykin, S.: Neural Networks, a comprehensive foundation, 2nd edn. Prentice Hall, Englewood Cliffs (1999)
Kohonen, T.: Self-Organizing maps, 3rd edn. Springer, Heidelberg (2000)
Flanagan, J.: Sufficiente conditions for self-organization in the SOM with a decreasing neighborhood function of any width. In: Conf. of Art. Neural Networks. Conf. pub. No. 470 (1999)
Erwin, E., Obermayer, K., Schulten, K.: Self-organizing maps: Ordering, convergence properties and energy functions. Biol. Cyb. 67, 47–55 (1992)
Kohonen, T., Kaski, S., Lappalainen, H.: Self-organized formation of various invariant-feature filters in the adaptive-subspace SOM. Neural Computation 9, 1321–1344 (1997)
Bishop, C., Svenson, M., Williams, C.: GTM: The Generative Topographic Mapping. Neural Computation 10, 215–234 (1999)
Ontrup, J., Ritter, H.: Hyperbolic Self-Organizing Maps for Semantic Navigation. Advances in Neural Information Processing Systems 14 (2001)
Bauer, H., Hermann, M., Villman, T.: Neural maps and topographic vector quantization. Neural Networks 12, 659–676 (1999)
Kiviluoto, K.: Topology preservation in Self-organizing Maps. In: Proc. of Int. Conf. on Neural Networks, ICNN 1996, vol. 1, pp. 294–299 (1996)
Villmann, T., Der, R., Herrmann, M., Martinetz, T.: Topology preservation in self-organizing maps: Exact definition and measurement. IEEE Trans. on Neural Networks 8, 256–266 (1997)
Watts, D., Strogatz, S.: Collective dynamics of ’small-world’ networks. Nature 393, 440–442 (1998)
Bollobás, B., Riordan, O.: Mathematical results on scale-free random graphs. In: Bornholdt, E., Schuster, G. (eds.) Handbook of graphs and networks, pp. 1–34. Wiley, Chichester (2002)
Strogatz, S.: Exploring complex networks. Nature 410, 268–276 (2001)
Barabási, A., Albert, R.: Emergence of scaling in random networks. Science 286, 509–512 (1999)
Grosse, I., Herzel, H., Buldyrev, S., Stanley, E.: Species dependence of mutual information in coding and noncoding DNA. Physical Review E 61, 5624–5630 (2000)
Shefi, O., Golding, I., Segev, R., Ben-Jacob, E., Ayali, A.: Morphological characterization of in vitro neuronal networks. Phys. Rev. E 66, 21905-1, 21905-5 (2002)
Quinlan, R.: C4.5: programs for machine learning. Morgan Kaufmann, San Francisco (1993)
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
Neme, A., Miramontes, P. (2005). Statistical Properties of Lattices Affect Topographic Error in Self-organizing Maps. 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_67
Download citation
DOI: https://doi.org/10.1007/11550822_67
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)