Advertisement

Geometric neural networks

  • Eduardo Bayro-Corrochano
  • Sven Buchholz
Visual and Motor Signal Neurocomputation
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1315)

Abstract

The representation of the external world in biological creatures appears to be defined in terms of geometry. This suggests that researchers should look for suitable mathematical systems with powerful geometric and algebraic characteristics. In such mathematical context the design and implementation of neural networks will be certainly more advantageous. This paper presents the generalization of feedforward neural networks in the Clifford or geometric algebra framework. The efficiency of the geometric neural nets indicate a step forward in the design of algorithms for multidimensional artificial learning.

Categories

Clifford algebra geometric algebra feedforward neural networks hyper-complex neural networks RBF geometric neural networks 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Arena P., Caponetto R., Fortuna L., Muscato G. and Xibilia M.G. 1996. Quaternionic multilayer perceptrons for chaotic time series prediction. IEICE Trans. Fundamentals. Vol. E79-A. No. 10 October, pp. 1–6.Google Scholar
  2. 2.
    Bayro-Corrochano E., Buchholz S., Sommer G. 1996. Selforganizing Clifford neural network IEEE ICNN'96 Washington, DC, June, pp. 120–125.Google Scholar
  3. 3.
    Bayro-Corrochano E., Lasenby J., Sommer G. Geometric Algebra: A framework for computing point and line correspondences and projective structure using nuncalibrated cameras IEEE Proceedings of ICPR'96 Viena, Austria, Vol. 1, pages 334–338, August, 1996.Google Scholar
  4. 4.
    Bayro-Corrochano E., Daniilidis K. and Sommer G. 1997. Hand-eye calibration in terms of motion of lines using Geometric Algebra. To appear in SCIA'97, June 9–11,Lappeenranta, Finland.Google Scholar
  5. 5.
    Cybenko G. Approximation by superposition of a sigmoidal function. Mathematics of control, signals and systems, Vol. 2, 303:314, 1989.Google Scholar
  6. 6.
    Doran C.J.L. 1994. Geometric algebra and its applications to mathematical physics. Ph.D. Thesis, University of Cambridge.Google Scholar
  7. 7.
    Georgiou G. M. and Koutsougeras C. Complex domain backpropagation. IEEE Trans. on Circuits and Systems, 330:334, 1992.Google Scholar
  8. 8.
    Hamilton W.R. 1853. Lectures on Quaternions. Hodges and Smith, Dublin.Google Scholar
  9. 9.
    Hestenes D. 1966. Space-Time Algebra. Gordon and Breach.Google Scholar
  10. 10.
    Hestenes D. and Sobczyk G. 1984. Clifford Algebra to Geometric Calculus: A unified language for mathematics and physics. D. Reidel, Dordrecht.Google Scholar
  11. 11.
    Hestenes D. 1993. Invariant body kinematics I: Saccadic and compensatory eye movements. Neural Networks, Vol. 7, 65–77.CrossRefGoogle Scholar
  12. 12.
    Hestenes D. 1993. Invariant body kinematics II: Reaching and neurogeometry. Neural Networks, Vol. 7, 79–88.CrossRefGoogle Scholar
  13. 13.
    Hornik K. 1989. Multilayer feedforward networks are universal approximators. Neural Networks, Vol. 2, pp. 359–366.CrossRefGoogle Scholar
  14. 14.
    Koenderink J. J. 1990. The brain a geometry engine. Psychological Research, Vol. 52, pp. 122–127.CrossRefPubMedGoogle Scholar
  15. 15.
    Pearson J. K. and Bisset D.L.. 1992. Back Propagation in a Clifford Algebra. Artificial Neural Networks, 2, I. Aleksander and J. Taylor (Ed.), 413:416.Google Scholar
  16. 16.
    Pellionisz A. and Llinás R. 1980. Tensorial approach to the geometry of brain function: cerebellar coordination via a metric tensor. Neuroscience Vol. 5, pp. 1125–1136CrossRefPubMedGoogle Scholar
  17. 17.
    Pellionisz A. and Llinás R. 1985. Tensor network theory of the metaorganization of functional geometries in th central nervous system. Neuroscience Vol. 16, No. 2, pp. 245–273.CrossRefPubMedGoogle Scholar
  18. 18.
    Perantonis S. J. and Lisboa P. J. G. 1992. Translation, rotation, and scale invariant pattern recognition by high-order neural networks and moment classifiers. IEEE Trans. on Neural Networks, Vol. 3, No. 2, March, pp 241–251.CrossRefGoogle Scholar
  19. 19.
    Poggio T. and Girosi F. Networks for approximation and learning. IEEE Proc., Vol. 78, No. 9, 1481:1497, Sept. 1990.CrossRefGoogle Scholar
  20. 20.
    Porteous I.R. 1995. Clifford Algebras and the Classical Groups. Cambridge University Press, Cambridge.Google Scholar
  21. 21.
    Sommer G., Bayro-Corrochano E. and Billow T. 1997. Geometric algebra as a framework for the perception-action cycle. Workshop on Theoretical Foundation of Computer Vision, Dagstuhl, March 13–19 1996, Springer Wien.Google Scholar
  22. 22.
    Rumelhart D.E. and McClelland J. L.. 1986. Parallel Distributed Processing: Explorations in the Microestructure of Cognition. 2 Vols. Cambridge: MIT Press.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Eduardo Bayro-Corrochano
    • 1
  • Sven Buchholz
    • 1
  1. 1.Computer Science Institute, Cognitive Systems GroupChristian Albrechts UniversityKielGermany

Personalised recommendations