Advertisement

Dynamic Allocation in Neural Networks for Adaptive Controllers

Chapter
  • 984 Downloads
Part of the Studies in Computational Intelligence book series (SCI, volume 268)

Abstract

Dynamic allocation in Neural Networks is the process of strategic addition of nodes during the evolution of a feature map. As the trend of using growing neural networks is rising in adaptive controller applications it is important to understand the robustness of the process of dynamic allocation in neural networks. In this paper we analyze the robustness of the process of dynamic allocation that are commonly utilized in growing neural networks to varying, and non-stationary input data. The analysis indicates that dynamic allocation in growing neural networks is not fully robust if based solely on the information from resource values or connectivity structure of the nodes. Based on the observations made, we propose a data-driven dynamic allocation algorithm that is useful for growing neural networks used in adaptive controller applications. The advantage of the proposed algorithm is that it allows neural networks to localize the information represented in the input data while ensuring that the overall topology of the data is preserved. Experimental results are presented to demonstrate using high-dimensional, multivariate data obtained from an adaptive flight controller simulator. The analytical and experimental results affirm the robustness and establish the precedence of the developed dynamic allocation algorithm for adaptive controller applications. We investigate the process of dynamic allocation in the Dynamic Cell Structures neural network algorithm, a representative growing neural network used for on-line learning in adaptive controllers, but the approach presented is applicable to any growing neural network where node insertion is performed in order to improve data modeling.

Keywords

Adaptive Controller High Resource Dynamic Allocation Lateral Connection Well Match Unit 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    van der Putten, P.: Utilizing the Topology Preserving Property of Self-Organizing Maps for Classification. M.S. Thesis. Cognitive Artificial Intelligence, Utrecht University, NL (1996)Google Scholar
  2. 2.
  3. 3.
    Fahlman, S.E.: CMU Benchmark Collection for Neural Net Learning Algorithms, Carnegie Mellon Univ, School of Computer Science, Machine-readable Data Repository, Pittsburgh (1993)Google Scholar
  4. 4.
    Perhinschi, M.G., Campa, G., Napolitano, M.R., Lando, M., Massotti, L., Fravolini, M.L.: A Simulation Tool for On-Line Real Time Parameter Identification. In: Proc. of the 2002 AIAA Modeling and Simulation Conference, Monterey (August 2002)Google Scholar
  5. 5.
    Fritzke, B.: Growing Self-organizing Networks - why? In: European Symposium on Artificial Neural Network, pp. 61–72 (1996)Google Scholar
  6. 6.
    Ahrns, I., Bruske, J., Sommer, G.: On-line Learning with Dynamic Cell Structures. In: Proc. of the International Conference on Artificial Neural Networks, vol. 2, pp. 141–146 (1995)Google Scholar
  7. 7.
    Bruske, J., Sommer, G.: Dynamic Cell Structures. In: Neural Information Processing Systems (NIPS1995), vol. 7, pp. 497–504 (1995)Google Scholar
  8. 8.
    Bruske, J., Sommer, G.: Dynamic Cell Structure Learns Perfectly Topology Preserving Map. Neural Computations 7(4), 845–865 (1995)CrossRefGoogle Scholar
  9. 9.
    Kohonen, T.: The Self-Organizing Map. Proc. of the IEEE 78(9), 1464–1480 (1990)CrossRefGoogle Scholar
  10. 10.
    Fritzke, B.: A Growing Neural Gas Network Learns Topologies. In: Advances in Neural Information Processing Systems, vol. 7, pp. 625–632. MIT Press, Cambridge (1995)Google Scholar
  11. 11.
    Fritzke, B.: Growing Grid - A Self-Organizing Network With Constant Neighborhood Range and Adaptation Strength. Neural Processing Letters 2(5), 9–13 (1995)CrossRefGoogle Scholar
  12. 12.
    Martinetz, T., Schulten, K.: Topology Representing Networks. Neural Networks 7(3), 507–522 (1994)CrossRefGoogle Scholar
  13. 13.
    Fritzke, B.: Growing Cell Structures - A Self-organizing Network for Unsupervised and Supervised Learning. ICSI 7(9), 1441–1460 (1993)Google Scholar
  14. 14.
    Jorgensen, C.: Feedback Linearized Aircraft Control Using Dynamic Cell Structures. In: World Automation Congress, ISSCI 050.1-050.6, Alaska (1991)Google Scholar
  15. 15.
    Fritzke, B.: Unsupervised Clustering With Growing Cell Structurea. In: Proc. of the IJCNN, pp. 531–536 (1991)Google Scholar
  16. 16.
    Kohonen, T.: The Self-Organizing Map. Proc. of the IEEE 78(9), 1464–1480 (1990)CrossRefGoogle Scholar
  17. 17.
    Farkas, I., Chud’y, L.: Modified Dynamic Cell Structures as a Thinning Algorithm. In: Sinc’ak, P. (ed.) Proc. of 1st Slovak Neural Network Symposium, November 1996, pp. 71–80 (1996)Google Scholar
  18. 18.
    Ahrns, I., Bruske, J., Sommer, G.: On-Line Learning with Dynamic Cell Structure. In: Proc. of International Conference on Artificial Neural Networks, vol. 2, pp. 141–146 (1995)Google Scholar
  19. 19.
    Bruske, J., Riehn, L., Hansen, M., Sommer, G.: Dynamic Cell Structures for Calibration–free Adaptive saccade control of a four-degrees-of-freedom binocular head. Technical Report TR-9608, Institut f. Informatik und Praktische Mathematik (1996)Google Scholar
  20. 20.
    Herpers, R., Witta, L., Bruske, J., Sommer, G.: Dynamic Cell Structures for the Evaluation of Keypoints in Facial Images. International Journal of Neural Systems 8(1), 27–39 (1997)CrossRefGoogle Scholar
  21. 21.
    Burcham Jr., F.W., Maine, T.A., Fullerton, C.G., Webb, L.D.: Development and flight evaluation of an emergency digital flight control system using only engine thrust on an F-15 airplane. Technical Report TR-3627, NASA (1996)Google Scholar
  22. 22.
    Napolitano, M., Neppach, C.D., Casdorph, V., Naylor, S., Innocenti, M., Silvestri, G.: A neural network-based scheme for sensor failure detection, identification, and accommodation. AIAA Journal of Control and Dynamics 18(6), 1280–1286 (1995)zbMATHCrossRefGoogle Scholar
  23. 23.
    Napolitano, M., Molinaro, G., Innocenti, M., Martinelli, D.: A complete hardware package for a fault tolerant flight control system using on-line learning neural networks. IEEE Control Systems Technology (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

There are no affiliations available

Personalised recommendations