Abstract
Starting from the problem of density estimation, it is shown that EM learning can be considered as a Hebbian mechanism. From this it is possible to outline a theory of self-organization of cortical maps which is based on a well defined optimization process and still preserves biologically desirable characteristics: local computation and uniform treatment of input and lateral connections.
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.
Similar content being viewed by others
References
M. Benaim. On Functional Approximation with Normalized Gaussian Units. Neural Computation, 6:319–333, 1994.
C.M. Bishop, M. Svensen, and K.I. Williams. GTM: a principled alternative to the self-organized map. In C. con der Malsburg, W. von Seelen, J.C. Vorbruggen, and B. Sendhoff, editors, Artificial Neural Networks, volume LCS-1112, pages 165–170, Berlin, 1996. Springer Verlag.
T.V.P. Bliss and G.L. Collinridge. A synaptic model of memory: long-term potentiation in the hippocampus. Nature, 361:31–39, 1993.
A.P. Dempster, N.M. Laird, and D.B. Rubin (1977). Maximum likelihood from incomplete data via EM algorithm. J. Royal Stat. Soc. B, 39:1–38, 1977.
F. Firenze and P. Morasso. The capture effect: a new self-organizing network for adaptive resolution clustering in changing environments. In IEEE World Congress on Computational Intelligence, volume 2, pages 653–658. IEEE Service Center, Piscataway, NJ, 1994.
D.O. Hebb. The organization of Behavior. J. Wiley, New York, 1949.
T. Kohonen. Self organization and associative memory. Springer-Verlag, Berlin, 1988.
T. Martinetz and K. Schulten. A’ Neural-Gas’ network learns topologies. In T. Kohonen, K. Makisara, O. Simula, and J. Kangas, editors, Artificial Neural Networks, pages 397–402, Amsterdam, 1991. North-Holland.
T. Martinetz and K. Schulten. Topology representing networks. Neural Networks, 7:507–522, 1994.
T. D. Sanger. A probability interpretation of neural population coding for movement. In P. Morasso and V. Sanguineti, editors, Self-organization, Computational Maps, and Motor Control, pages 75–116. Elsevier Science Publishers, Amsterdam, 1997.
V. Sanguineti, P. Morasso, and F. Frisone. Cortical maps of sensorimotor spaces. In P. Morasso and V. Sanguineti, editors, Self-organization, Computational Maps, and Motor Control, pages 1–36. Elsevier Science Publishers, Amsterdam, 1997.
L. Xu and M. I. Jordan. On convergence properties of the EM Algorithm for Gaussian mixtures. Neural Computation, 8:129–151, 1996.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag London Limited
About this paper
Cite this paper
Frisone, F., Morasso, P.G. (1999). Soft-competitive versus EM learning in cortical map modeling. In: Marinaro, M., Tagliaferri, R. (eds) Neural Nets WIRN VIETRI-98. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-0811-5_9
Download citation
DOI: https://doi.org/10.1007/978-1-4471-0811-5_9
Publisher Name: Springer, London
Print ISBN: 978-1-4471-1208-2
Online ISBN: 978-1-4471-0811-5
eBook Packages: Springer Book Archive