Advertisement

AMI: A model of intelligence

  • D. B. Hoang
  • M. R. James
Neural Nets and Uncertainty I
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1114)

Abstract

It is reasonable to say that so far neural networks have performed very well on many specific tasks of reasonable size, but their performance is far from satisfactory when applied to realistic but complex tasks such speech recognition and language processing. Yet the brain can perform these tasks efficiently and effortlessly (seemingly) using its optimized mechanisms. It is believed crucial to discover these mechanisms. In this paper, a neural network model of the isocortex as basic building block of intelligent systems is consolidated. The model incorporates mechanisms extracted from cortical circuit as suggested from the study of neuroanatomy. The learning rule compatible with what is known about synaptic adaptation in the neocortex is introduced. Simulations results, which verify the mathematical proof of the model stability and robustness, are presented.

Keywords

Intelligent systems neural networks learning algorithms neocortex 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    James, M., and Hoang, D. B., “Outline of a theory of Isocortex,” Chapter 69, Computation and Neural Systems, Eeckman and Bower (Eds), Kluwer Academic Publishers, 1993.Google Scholar
  2. 2.
    Hoang D B, James M, “A Neural Network Model of Isocortex”, Proceedings of the fifth Australian conference on Neural Networks, ACNN'94, Brisbane, Feb. 1994, pp. 173–176.Google Scholar
  3. 3.
    Hoang, D. B., and James. M., “Stability of a basic biological neural circuit”, Proceedings of the IEEE International Conference on Neural Networks, ICNN'95, Perth, Nov. 1995, pp.1981–1985.Google Scholar
  4. 4.
    James, M., and Hoang, D.B.,“Pattern learning in a cortical circuit”, Proceedings of the Fourth Annual Computation Neuroscience Meeting CNS*95, July 1995, California. (in press)Google Scholar
  5. 5.
    Burkhalter, A.,”Intrinsic Connections of Rat Primary Visual Cortex: Laminar Organization of Axional Projections,” Journal of Comparative Neurology, Vol. 279, 1989, pp. 171–186.Google Scholar
  6. 6.
    Von der Malsburg, C., “Self-organization of orientation sensitive cells in the striate cortex,” Kybernetik, Vol. 14, 1973, pp. 85–100.Google Scholar
  7. 7.
    Kohonen, T., Self-organization and Associative Memory, Second Edition, Berlin, Springer-Verlag, 1988.Google Scholar
  8. 8.
    Carpenter, G. A., and Grossberg, S., “ART2: Self-organization of stable category recognition codes for analog input patterns”, Applied Optics, Vol. 26, 1987, pp. 4919–4930.Google Scholar
  9. 9.
    Murre, J. M. J., Phaf, H., and Wolters, G., “CALM: Categorizing and Learning Module.” Neural Networks, Vol. 5, 1992, pp. 55–82.Google Scholar
  10. 10.
    Bienenstock, E. L., Cooper, L. N., and Munro, P. W., “Theory for the development of neural selectivity: Orientation specificity and binocular interaction in visual cortex.” Journal Neuroscience, Vol. 2, 1982, pp. 32–48.Google Scholar
  11. 11.
    Clothiaux, B., Bear, M. F., and Cooper, L. N., “Synaptic plasticity in visual cortex: Comparison of theory with experiment.” Journal of Neurophysiology, Vol. 66, No. 5, 1991, pp. 1785–1804.Google Scholar
  12. 12.
    James, M., and Hoang, D.B.,“An Adaptive Model of the Cortical Circuit”, Proceedings of the seventh Australian conference on Neural Networks, ACNN'96, Canberra, 1996, pp.206–211.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • D. B. Hoang
    • 1
  • M. R. James
    • 1
  1. 1.Basser Department of Computer ScienceUniversity of SydneyAustralia

Personalised recommendations