Advertisement

Knowledge acquisition on neural networks

  • Su-shing Chen
Neural Nets
Part of the Lecture Notes in Computer Science book series (LNCS, volume 313)

Abstract

A knowledge acquisition system is implemented on the IBM PAN (Parallel Associative Networks) system. This is an iterative process that reduces the uncertainty of a body of knowledge and information at each time step and produces a convergent result which provides certainty to this body. This scheme of uncertainty management is similar to human thinking and decision making processes. The characteristics of noncrisp (or fuzzy) and multi-valued reasoning and gradual improvement of understanding are captured by a mathematically rigorous model which is implemented conveniently on a neural network processor.

Keywords

Bayesian Network Knowledge Acquisition Probabilistic Logic Fuzzy Subset Propositional Variable 
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.
    S. Chen, Evidential logic and Dempster-Shafer theory, Proc. ACM SIGART International Symposium of Methodologies for Intelligent Systems, Knoxville, Tenn., Oct.22–24, 1986, 201–206.Google Scholar
  2. 2.
    S. Chen, Some extensions of probabilistic logic, Proc. AAAI Workshop on Uncertainty in Artificial Intelligence, Philadelphia, Penn., August 8–10, 1986, 43–48. An extended version will appear in Uncertainty in Artificial Intelligence. Vol. 2, edited by L. N. Kanal and J. F. Lemmer, North-Holland.Google Scholar
  3. 3.
    S. Chen and C. Cruz-Young, Evidential reasoning on parallel associative networks.Google Scholar
  4. 4.
    C. A. Cruz and H. J. Myers, Associative Networks, IBM Palo Alto Scientific Center Report ZZ20-6459, October, 1982.Google Scholar
  5. 5.
    C. A. Cruz and H. J. Myers, Associative Networks II, IBM Palo Alto Scientific Center Report G320-3446, 1983.Google Scholar
  6. 6.
    A. P. Dempster, A generalization of Bayesian inference, Journal of the Royal Statistical Society, Series B, 30 (1968), 205–247.Google Scholar
  7. 7.
    J. Gordon and E. H. Shortliffe, A method for managing evidential reasoning in a hierarchical hypothesis space, Artificial Intelligence, 26 (1985), 323–357.Google Scholar
  8. 8.
    R. A. Hummel and S. W. Zucker, On the foundations of relaxation labeling processes, IEEE Trans. PAMI, 5 (1983), 267–287.Google Scholar
  9. 9.
    M. S. Landy and R. A. Hummel, A brief survey of knowledge aggregation methods, New York University, Courant Institute Technical Note 177, September 1985.Google Scholar
  10. 10.
    J. Lowrance and T. Garvey, Evidential reasoning: An implementation for multisensor integration, SRI AI Center Tech. Note 307, December 1983.Google Scholar
  11. 11.
    J. Lukasiewicz, Logical foundations of probability theory, Jan Lukasiewicz Selected Works, ed. by L. Berkowski, North-Holland, 1970, 16–43.Google Scholar
  12. 12.
    N. J. Nilsson, Probabilistic logic, Artificial Intelligence, 28 (1986), 71–87.Google Scholar
  13. 13.
    J. Pearl, On evidential reasoning in a hierarchy of hypotheses, Artificial Intelligence, 28 (1986), 9–15.Google Scholar
  14. 14.
    J. Pearl, Fusion, propagation, and structuring in Bayesian networks, UCLA Technical Notes, April 1985.Google Scholar
  15. 15.
    J. Pearl, Distributed revision of belief commitment in multi-hypotheses interpretations, Proc. AAAI Workshop on Uncertainty in Artificial Intelligence, Philadelphia Penn, August 8–10, 1986, 201–210.Google Scholar
  16. 16.
    A. Rosenfeld, R. A. Hummel and S. W. Zucker, Scene labeling by relaxation operations, IEEE Trans. Systems, Man and Cybernetics, 6 (1976), 420–433.Google Scholar
  17. 17.
    G. A. Shafer, Mathematical Theory of Evidence, Princeton University Press, 1979.Google Scholar
  18. 18.
    L. A. Zadeh, Fuzzy logic and approximating reasoning, Synthese, 30 (1975), 407–428.Google Scholar
  19. 19.
    G. E. Hinton and J. A. Anderson, Parallel Models of Associative Memory, L. Erlbaum Associates, Hillsdale, New Jersey, 1981.Google Scholar
  20. 20.
    J. L. McClelland, D. E. Rumelhart and the PDP Research Group, Parallel Distributed Processing, The MIT Press, 1986.Google Scholar
  21. 21.
    S. Chen, Automated reasoning on neural networks: A probabilistic approach, Proc. IEEE First Annual International Conference on Neural Networks, San Diego, 1987.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1988

Authors and Affiliations

  • Su-shing Chen
    • 1
  1. 1.Department of Computer ScienceUniversity of North CarolinaCharlotte

Personalised recommendations