Abstract
In this paper, we propose a new objective function for forming topographic mappings, named the “InfoMin” criterion. This criterion is defined as the average of the information transferred through small neighbor areas over a mapping, and its closed form is derived by use of the Edgeworth expansion. If the second-order statistics (namely, normal correlations among neurons) are not zero, the InfoMin criterion is consistent with the C measure (a unifying objective function for topographic mapping proposed by Goodhill and Sejnowski [1]). In addition, the higher-order correlations are dominant in this criterion only if the second-order ones are negligible. So, it can explain many previous models comprehensively, and is applicable to uncorrelated signals such that ZCA or ICA generates as well. Numerical experiments on natural scenes verify that the InfoMin criterion gives a strong unifying framework for topographic mappings based on information theory.
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
Goodhill, G. J. & Sejnowski, T. (1997). A Unifying Objective Function for Topographic Mappings Neural Computation, 9, 1291–1303.
Tootell, R. B. H., Switkes, E., & Silverman, M. S. (1988). Functional anatomy of macaque striate cortex, II, Retinotopic organization. The Journal of Neuroscience, 8(5), 1531–1568.
Hubel, D. H., & Wiesel, T. N. (1977). Functional Architecture of macaque monkey visual cortex. Proceedings of the Royal Society of London B, 198, 1–59.
Swindale, N. V. (1996). The development of topography in the visual cortex: A review of models. Network: Computation in Neural Systems, 7(2), 161–247.
Erwin, E., Obermayer, K., & Schulten, K. (1995). Models of orientation and ocular dominance columns in the visual cortex: A critical comparison. Neural Computation, 7, 425–468.
Wiskott, L. & Sejnowski, T. J. (1998). Constrained optimization for neural map formation: A unifying framework for weight growth and normalization. Neural Computation, 10, 671–716.
Li, Z. & Atick, J. J. (1994). Toward a theory of the striate cortex. Neural Computation 6(1), 127–146.
Hyvärinen, A., Hoyer, P. O., & Inki, M. (2001). Topographic independent component analysis. Neural Computation, 13(7), 1527–1558.
Linsker, R. (1988). Self-organization in a Perceptual Network. Computer, 21(3), 105–117.
Plumbley, M. (1993). Efficient information transfer and anti-Hebbian neural networks. Neural Networks, 6, 823–833.
Bell, A. J. & Sejnowski, T. J. (1997). The independent components of natural scenes are edge filters. Vision Research 37(23), 3327–3338.
Linsker, R. (1989). How to generate ordered maps by maximizing the mutual information between input and output signals. Neural Computation, 1, 402–411.
Luttrell, S. P. (1994). A Bayesian analysis of self-organizing maps. Neural Computation, 6, 767–794.
Bishop, C. M., Svensen, M., & Williams, C. K. I. (1998). GTM: The generative topographic mapping. Neural Computation, 10(1), 215–234.
Matsuda, Y., & Yamaguchi, K. (2001). The InfoMin principle: A unifying information-Based criterion for forming topographic Mappings. in Proceedings of ICONIP, Shanghai, China, 14–19.
Barndorff-Nielsen, O. E. & Cox, D. R. (1989). Asymptotic techniques for use in statistics. London; New York: Chapman and Hall.
Durbin, R. & Mitchson, G. (1990). A dimension reduction framework for understanding cortical maps. Nature, 343, 644–647.
Kirkpatrick, S., Gelatt, C. D., & Vecchi, M. P. (1983). Optimization by simulated annealing. Science, 220, 671–680.
Hyvärinen, A. (1999). Fast and robust fixed-point algorithms for independent component analysis. IEEE Transactions on Neural Networks, 10, 626–634.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Matsuda, Y., Yamaguchi, K. (2003). The InfoMin Criterion: An Information Theoretic Unifying Objective Function for Topographic Mappings. In: Kaynak, O., Alpaydin, E., Oja, E., Xu, L. (eds) Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003. ICANN ICONIP 2003 2003. Lecture Notes in Computer Science, vol 2714. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44989-2_48
Download citation
DOI: https://doi.org/10.1007/3-540-44989-2_48
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40408-8
Online ISBN: 978-3-540-44989-8
eBook Packages: Springer Book Archive