Abstract
We present a method for calculating phase diagrams for the high-dimensional variant of the Self-Organizing Map (SOM). The method requires only an ansatz for the tesselation of the data space induced by the map, not for the explicit state of the map. Using this method we analyze two recently proposed models for the development of orientation and ocular dominance column maps. The phase transition condition for the orientation map turns out to be of different form than of the corresponding low-dimensional map.
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.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
T. Kohonen, Self-Organizing Maps, Springer, Berlin (1995).
C. von der Malsburg, Kybernetik 14, 85 (1973); Biol. Cyb. 32, 49 (1979).
K. D. Miller, J. Neurosci. 14, 409 (1994).
K. Obermayer, H. Ritter, K. Schulten, Proc. Nat. Acad. Sci. USA 87, 8345 (1990).
H.-U. Bauer, M. Riesenhuber, T. Geisel, submitted to Phys. Rev. Letters (1995).
M. Riesenhuber, H.-U. Bauer, T. Geisel, submitted to Biol. Cyb. (1995).
E. Erwin, K. Obermayer, K. Schulten, Biol. Cyb. 67, 47 (1992).
K. Obermayer, Adaptive Neuronale Netze und ihre Anwendung als Modelle der Entwicklung kortikaler Karten, infix Verlag, Sankt Augustin (1993).
K. Obermayer, G. G. Blasdel, K. Schulten, Phys. Rev. A 45, 7568 (1992).
K. Pawelzik, H.-U. Bauer, F. Wolf, T. Geisel, Proc. ICANN 96, this volume (1996).
G. J. Goodhill, Biol. Cyb. 69, 109 (1993).
S. Löwel, J. Neurosci. 14, 7451 (1994).
G. J. Goodhill, D. J. Willshaw, Network 1, 41 (1990); P. Dayan, Neur. Comp. 5, 392 (1993).
M. Riesenhuber, H.-U. Bauer, T. Geisel, submitted to CNS 96, Boston (1996).
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Riesenhuber, M., Bauer, HU., Geisel, T. (1996). Analyzing the formation of structure in high-dimensional Self-Organizing Maps reveals differences to feature map models. In: von der Malsburg, C., von Seelen, W., Vorbrüggen, J.C., Sendhoff, B. (eds) Artificial Neural Networks — ICANN 96. ICANN 1996. Lecture Notes in Computer Science, vol 1112. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61510-5_71
Download citation
DOI: https://doi.org/10.1007/3-540-61510-5_71
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61510-1
Online ISBN: 978-3-540-68684-2
eBook Packages: Springer Book Archive