Advertisement

Neural Networks for Rapid Learning in Computer Vision and Robotics

  • H. Ritter
Conference paper
Part of the International Centre for Mechanical Sciences book series (CISM, volume 382)

Abstract

One of the major thrusts for the success of neural networks in many areas was the development of learning algorithms that allow to capture implicit knowledge that is only available in the form of examples such that it can be generalized and applied to new situations, usually “inputs” to a suitably trained net.

Keywords

Joint Angle Inverse Kinematic Support Point Gabor Wavelet Step Size Parameter 
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. [CV95]
    C. Cortes and V. Vapnik. Support-vector networks. Machine Learning, 20 (3): 273–297, 1995.MATHGoogle Scholar
  2. [Dau80]
    J. G. Daugman. Two-dimensional spectral analysis of cortical receptive field profiles. Vision Research, 20: 847–856, 1980.CrossRefGoogle Scholar
  3. [FGL87]
    K.S. Fu, R.C. Gonzalez, and C.S.G. Lee. Robotics. McGraw-Hill, New York, 1987.Google Scholar
  4. [GJP95]
    Frederico Girosi, Michael Jones, and Tomaso Poggio. Regularization theory and neural networks architectures. Neural Computation, 7: 219–269, 1995.CrossRefGoogle Scholar
  5. [HKRS96]
    Gunther Heidemann, Franz Kummert, Helge Ritter, and Gerhard Sagerer. A hybrid object recognition architecture. In ICANN 96, Springer Lecture Notes in Computer Science 1112, pages 305–310. Springer Verlag, Berlin, 1996.Google Scholar
  6. [JJ94]
    M.I. Jordan and R.A. Jacobs. Hierarchical mixtures of experts and the EM algorithm. Neural Computation, 6 (2): 181–214, 1994.CrossRefGoogle Scholar
  7. [JJNH91]
    R.A. Jacobs, M.I. Jordan, S.J. Nowlan, and G.E. Hinton. Adaptive mixtures of local experts. Neural Computation, 3: 79–87, 1991.CrossRefGoogle Scholar
  8. [Koh90]
    T. Kohonen. The self-organizing map. Proceedings IEEE, 78: 1464–1480, 1990.CrossRefGoogle Scholar
  9. [LR97]
    Enno Littmann and Helge Ritter. Adaptive color segmentation — a comparison of neural and statistical methods. IEEE Transactions on Neural Networks, pages 175–185, 1997.Google Scholar
  10. [MD88]
    J. Moody and C. Darken. Learning with localized receptive fields. In Connectionist Models: Proceedings of the 1988 Summer School, pages 133–143. Morgan Kaufman Publishers, San Mateo, CA, 1988.Google Scholar
  11. [MR92]
    Andrea Meyering and Helge Ritter. Learning 3d-shape-perception with local linear maps. In Proceedings of the International Joint Conference on Neural Networks, pages IV:432–436, Baltimore, 1992.Google Scholar
  12. [PFTV90]
    W.H. Press, B.P. Flannery, S.A. Teukolsky, and W.T. Vetterling. Numerical Recipes in C. Cambridge University Press, Cambridge, 1990.Google Scholar
  13. [Rit93]
    Helge Ritter. Parametrized self-organizing maps. In S. Gielen and B. Kappen, editors, ICANN 93-Proceedings, pages 568–577, Berlin, 1993. Springer.Google Scholar
  14. [RMS92]
    Helge Ritter, Thomas Martinetz, and Klaus Schulten. Neural Computation and Self-organizing Maps. Addison Wesley, [1. revised english edition] edition, 1992.Google Scholar
  15. [RS87]
    Helge Ritter and Klaus Schulten. Extending kohonen’s self-organizing mapping algorithm to learn ballistic movements. In Eckmiller R. and von der Malsburg C, editors, Neural Computers, pages 393–406, Heidelberg, 1987. Springer.Google Scholar
  16. [SU90]
    K. Stokbro and D.K. Umberger. Forecasting with weighted maps. In Martin Casdagli and Stephen Eubank, editors, Nonlinear Modeling and Forecasting, volume 4, pages 73–98. Addison-Wesley, 1990.Google Scholar
  17. [Wa196]
    Jörg Walter. Rapid Learning in Robotics. Cuvillier Verlag Göttingen, 1996. also www.techfak.uni-bielefeld.de/~waiter/pub/~waiter/pub/
  18. [WR95]
    Jörg Walter and Helge Ritter. Local PSOMs and Chebyshev PSOMs — improving the parametrised self-organizing maps. In Proc. Int. Conf. on Artificial Neural Networks (ICANN-95), Paris, volume 1, pages 95–102, 1995.Google Scholar
  19. [WR96a]
    Jörg Walter and Helge Ritter.. Investment learning with hierarchical PSOM. In D. Touretzky, M. Mozer, and M. Hasselmo, editors, Advances in Neural Information Processing Systems 8 (NIPS*95), pages 570–576. Bradford MIT Press, 1996.Google Scholar
  20. [WR96b]
    Jörg Walter and Helge Ritter. Rapid learning with parametrized self-organizing maps. Neurocomputing, pages 131–153, 1996.Google Scholar
  21. [YB93]
    D. Yeung and G. Bekey. on reducing learning time in context dependent mappings. IEEE Transactions on Neural Networks, 4: 31–42, 1993.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Wien 1997

Authors and Affiliations

  • H. Ritter
    • 1
  1. 1.Bielefeld UniversityBielefeldGermany

Personalised recommendations