Abstract
Lateral and elastic interactions are known to build a topology in different systems. We demonstrate how the models with weak lateral interactions can be reduced to the models with corresponding weak elastic interactions. Namely, the batch version of soft topology-preserving map can be rigorously reduced to the elastic net. Owing to the latter, both models produce similar behaviour when applied to the TSP. Unlike, the incremental (online) version of soft topology-preserving map is reduced to the cortical map only in the limit of low temperature, which makes their behaviours different when applied to the ocular dominance formation.
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
Hertz, J., Krogh, A., Palmer, R.G.: Introduction to the Theory of Neural Computation. Addison-Wesley, Reading, London, UK (1991)
Kohonen, T.: Self-Organized Formation of Topologically Correct Feature Maps. Biological Cybernetics 43, 59–69 (1982)
Durbin, R., Willshaw, D.: An Analogue Approach to the Travelling Salesman Problem Using an Elastic Net Method. Nature 326, 689–691 (1987)
Durbin, R., Mitchison, G.: A Dimension Reduction Framework for Understanding Cortical Maps. Nature 343, 644–647 (1990)
Tereshko, V.: Topology-Preserving Elastic Nets. In: Mira, J.M., Prieto, A.G. (eds.) IWANN 2001. LNCS, vol. 2084, pp. 551–557. Springer, Heidelberg (2001)
Tereshko, V., Allinson, N.M.: Combining Lateral and Elastic Interactions: Topology-Preserving Elastic Nets. Neural Processing Letters 15, 213–223 (2002)
Tereshko, V.: Modelling Topology Preservation in a Cortex by Controlled Deformation of Its Energy Landscape. Neurocomputing 44-46C, 667–672 (2002)
Tereshko, V.: Deriving cortical maps and elastic nets from topology-preserving maps. In: Cabestany, J., Priet, A., Sandoval, F. (eds.) IWANN 2005. LNCS, vol. 3512, pp. 326–332. Springer, Heidelberg (2005)
Graepel, T., Burger, M., Obermayer, K.: Phase Transitions in Stochastic Self-Organizing Maps. Phys. Rev. E 56, 3876–3890 (1997)
Heskes, T.: Energy Functions for Self-Organizing Maps. In: Oja, E., Kaski, S. (eds.) Kohonen Maps, pp. 303–315. Elsevier, Amsterdam (1999)
Goodhill, G.J. (ed.): Correlations, Competition, and Optimality: Modelling the Development of Topography and Ocular Dominance. Cognitive Science Research Paper 226. University of Sussex, Brighton (1992)
Swindale, N.V.: The Development of Topography in the Visual Cortex: a Review of Models. Comput. Neur. Syst. 7, 161–247 (1996)
Mitchison, G.: Neuronal Branching Patterns and the Economy of Cortical Wiring. Proc. Roy. Soc. B. 245, 151–158 (1991)
Simic, P.D.: Statistical Mechanics as the Underlying Theory of “Elastic” and “Neural” Optimisations. Network: Comput. Neur. Syst. 1, 89–103 (1990)
van den Berg, J.: Neural Relaxation Dynamics: Mathematics and Physics of Recurrent Neural Networks with Applications in the Field of Combinatorial Optimization. PhD Thesis. Erasmus University, Rotterdam (1996)
Folk, R., Kartashov, A.: A simple elastic model for self-organizing topological mappings. Network. Computation in Neural Systems 5, 369–387 (1994)
Wong, Y.: A Comparative study of the Kohonen self-organizing map and the elastic net. In: Hanson, S.J., Petsche, T., Kearns, M., Rivest, R.L. (eds.) Computational Learning Theory and Natural Learning Systems, vol. 2, pp. 401–413. MIT, Cambridge (1994)
Mitchison, G.: A Type of duality between self-organizing maps and minimal wiring. Neural Computation 7, 25–35 (1995)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tereshko, V. (2007). Lateral and Elastic Interactions: Deriving One Form from Another. In: de Sá, J.M., Alexandre, L.A., Duch, W., Mandic, D. (eds) Artificial Neural Networks – ICANN 2007. ICANN 2007. Lecture Notes in Computer Science, vol 4669. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74695-9_7
Download citation
DOI: https://doi.org/10.1007/978-3-540-74695-9_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74693-5
Online ISBN: 978-3-540-74695-9
eBook Packages: Computer ScienceComputer Science (R0)