Movatterモバイル変換

[0]ホーム
URL:

Skip to main content

Advertisement

Springer Nature Link
Log in

Enhancing Topology Preservation during Neural Field Development Via Wiring Length Minimization

  • Conference paper

Part of the book series:Lecture Notes in Computer Science ((LNTCS,volume 5163))

Included in the following conference series:

Abstract

We recently proposed a recurrent neural network model for the development of dynamic neural fields [1]. The learning regime incorporates homeostatic processes, such that the network is able to self-organize and maintain a stable operation mode even in face of experience-driven changes in synaptic strengths. However, the learned mappings do not necessarily have to be topology preserving. Here we extend our model by incorporating another mechanism which changes the positions of neurons in the output space. This algorithm operates with a purely local objective function of minimizing the wiring length and runs in parallel to the above mentioned learning process. We experimentally show that the incorporation of this additional mechanism leads to a significant decrease in topological defects and further enhances the quality of the learned mappings. Additionally, the proposed algorithm is not limited to our network model; rather it can be applied to any type of self-organizing maps.

This is a preview of subscription content,log in via an institution to check access.

Access this chapter

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Gläser, C., Joublin, F., Goerick, C.: Homeostatic development of dynamic neural fields. In: Proc. International Conference on Development and Learning (2008)

    Google Scholar 

  2. Kangas, J.: Utilizing the similarity preserving properties of self-organizing maps in vector quantization of images. In: Proc. International Conference on Neural Networks, vol. 4, pp. 2081–2084 (1995)

    Google Scholar 

  3. Vörös, T., Keresztényi, Z., Fazekas, C., Laczkó, J.: Computer aided interactive remote diagnosis using self-organizing maps. In: Proc. 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, vol. 5, pp. 3190–3193 (2004)

    Google Scholar 

  4. Alhoniemi, E., Hollmén, J., Simula, O., Vesanto, J.: Process monitoring and modeling using the self-organizing map. Integrated Computer-Aided Engineering 6(1), 3–14 (1999)

    Google Scholar 

  5. Herrmann, M.: Self-organizing feature maps with self-organizing neighborhood widths. In: Proc. International Conference on Neural Networks, pp. 2998–3003 (1995)

    Google Scholar 

  6. Phaf, R., Den Dulk, P., Tijsseling, A., Lebert, E.: Novelty-dependent learning and topological mapping. Connection Science 13(4), 293–321 (2001)

    Article  Google Scholar 

  7. Kirk, J.S., Zurada, J.M.: Algorithms for improved topology preservation in self-organizingmaps. In: Proc. International Conference on Systems, Man, and Cybernetics, vol. 3, pp. 396–400 (1999)

    Google Scholar 

  8. Amari, S.: Dynamics of pattern formation in lateral-inhibition type neural fields. Biological Cybernetics 27, 77–87 (1977)

    Article MATH MathSciNet  Google Scholar 

  9. Williams, S., Stuart, G.: Role of dendritic synapse location in the control of action potential output. Trends in Neuroscience 26(3), 147–154 (2003)

    Article  Google Scholar 

  10. Kiviluoto, K.: Topology preservation in self-organizing maps. In: Proc. International Conference on Neural Networks, vol. 1, pp. 294–299 (1996)

    Google Scholar 

  11. Kirk, J.S., Zurada, J.M.: A two-stage algorithm for improved topography preservation in self-organizing maps. In: Proc. International Conference on Systems, Man, and Cybernetics, vol. 4, pp. 2527–2532 (2000)

    Google Scholar 

  12. Villmann, T., Der, R., Herrmann, M., Martinetz, T.M.: Topology preservation in self-organizing feature maps: Exact definition and measurement. IEEE Transactions on Neural Networks 8(2), 256–266 (1997)

    Article  Google Scholar 

  13. Kohonen, T.: Self-organized formation of topologically correct feature maps. Biological Cybernetics 43, 59–69 (1982)

    Article MATH MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Honda Research Institute Europe,  , Carl-Legien-Str. 30, D-63073, Offenbach/Main, Germany

    Claudius Gläser, Frank Joublin & Christian Goerick

Authors
  1. Claudius Gläser

    You can also search for this author inPubMed Google Scholar

  2. Frank Joublin

    You can also search for this author inPubMed Google Scholar

  3. Christian Goerick

    You can also search for this author inPubMed Google Scholar

Editor information

Véra Kůrková Roman Neruda Jan Koutník

Rights and permissions

Copyright information

© 2008 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Gläser, C., Joublin, F., Goerick, C. (2008). Enhancing Topology Preservation during Neural Field Development Via Wiring Length Minimization. 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_61

Download citation

Publish with us

[8]ページ先頭
©2009-2025 Movatter.jp