Abstract
Decreasing neighborhood has been identified as a necessary condition for self-organization to hold in the self-organizing map (SOM). In the SOM, each best matching unit (BMU) decreases its influence area as a function of time and this area is always radial. Here, we present a model in which the BMU does not reduce its neighborhood, but the rest of the neurons exclude some BMUs from affecting them. In this model, what decreases as a function of time is the number of BMUs that affect each neuron, not the neighborhood of the BMUs. Each neuron identifies, from the set of BMUs that influenced it during each epoch, the farthest one and becomes refractory to it for the rest of the process. This BMU exclusion is not equivalent to the original decreasing neighborhood scheme. Even though the decreasing neighborhood condition is not totally maintained, self-organization remains, as shown by several experiments.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Cottrell, M., Fort, J.C., Pagés, G.: Theoretical aspects of the SOM algorithm. Neurocomputing 21, 119–138 (1998)
Kohonen, T.: Self-Organizing maps, 3rd edn. Springer, Heidelberg (2000)
Ritter, H.: Self-Organizing Maps on non-euclidean Spaces Kohonen Maps. Oja, E., Kaski, S. (eds.), pp. 97–108 (1999)
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, Obermayer, K., Schulten, K.: Self-organizing maps: Ordering, convergence properties and energy functions. Biol. Cyb. 67, 47–55 (1992)
Berglund, E., Sitte, J.: The parameterless Self-Organizing Map Algorithm. IEEE Trans. on Neural networks 17(2), 305–316 (2006)
Miikkulainen, R., Bednar, J., Choe, Y., Sirosh, J.: Computational maps in the visual cortex. Springer, New York (2005)
Rakic, S., Zecevic, N.: Emerging complexity of layer I in human cerebral cortex. Cerebral Cortex 13, 1072–1083 (2003)
Shefi, O., Golding, I., Segev, R., Ben-Jacob, E., Ayali, A.: Morphological characterization of in vitro neuronal networks. Phys. Rev. E 66, 21905(1–5) (2002)
Bailey, C., Kandel, E., SI, K.: The persistence of long-term memory. Neuron 44, 49–57 (2004)
Aoki, T., Aoyagi, T.: Self-organizing maps with asymmetric neighborhood function. Neural computation 19(9), 2515–2535 (2007)
Neme, A., Miramontes, P.: A parameter in the SOM learning rule that incorporates activation frequency. ICANN (1), 455–463 (2006)
Lee, J., Verleysen, M.: Self-organizing maps with recursive neighborhood adaption. Neural Networks 15, 993–1003 (2002)
Kiviluoto, K.: Topology preservation in Self-Organizing maps. In: Proc. ICNN 1996, IEEE Int. Conf. on Neural Networks (1996)
Almeida, J., Carrico, J., Maretzek, A., Noble, P., Fletcher, M.: Analysis of genomic sequences by chaos game representatio. Bioinformatics 17(5), 429–437 (2001)
Jeffrey, J.: Chaos game representation of sequences in Chaos and Fractals: a computer graphical journey. Pickover (1998)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Neme, A., Chavez, E., Cervera, A., Mireles, V. (2008). Decreasing Neighborhood Revisited in Self-Organizing Maps. In: Kůrková, V., Neruda, R., Koutník, J. (eds) Artificial Neural Networks - ICANN 2008. ICANN 2008. Lecture Notes in Computer Science, vol 5163. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87536-9_69
Download citation
DOI: https://doi.org/10.1007/978-3-540-87536-9_69
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-87535-2
Online ISBN: 978-3-540-87536-9
eBook Packages: Computer ScienceComputer Science (R0)