Skip to main content
SpringerLink
Log in

Expert networks: Paradigmatic conflict, technological rapproachement

  • General Articles
  • Published:
Minds and Machines Aims and scope Submit manuscript

Abstract

A rule-based expert system is demonstrated to have both a symbolic computational network representation and a sub-symbolic connectionist representation. These alternate views enhance the usefulness of the original system by facilitating introduction of connectionist learning methods into the symbolic domain. The connectionist representation learns and stores metaknowledge in highly connected subnetworks and domain knowledge in a sparsely connected expert network superstructure. The total connectivity of the neural network representation approximates that of real neural systems and hence avoids scaling and memory stability problems associated with other connectionist models.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Buchanan, B. G. and Shortliffe, E. H. (1984),Rule-Based Expert Systems: The MYCIN Experiments of the Stanford Heuristic Programming Project, Addison-Wesley, Reading, MA.

    Google Scholar 

  • Churchland, P. M. and Churchland, P. S. (1990), ‘Could a Machine Think?’,Scientific American 262, pp. 32–39.

    Google Scholar 

  • Dagli, C. H. and Stacey, R. (1988), ‘A Prototype Expert System for Selecting Control Charts’,Int. J. Prod. Res. 26, pp. 987–996.

    Google Scholar 

  • Eberhardt, S. P., Duong, T., and Thakoor, A. P. (1989a), ‘A VLSI “Building Block” Chip for Hardware Neural Network Implementations’,Proceedings Third Annual Parallel Processing Symposium, Vol. I, IEEE Orange County Computer Society, Fullerton, CA, pp. 257–267.

    Google Scholar 

  • Eberhardt, S. P., Duong, T., and Thakoor, A. P. (1989b), ‘Design of Parallel Hardware Neural Network Systems from Custom Analog VLSI “Building Block” Chips’,Proceedings IJCNN 89 (Washington, DC), Vol. II, IEEE, Piscataway, NJ, pp. 183–190.

    Google Scholar 

  • Eberhardt, S. P., Daud, T., Kerns, D. A., Brown, T. X., and Thakoor, A. P. (1991), ‘Competitive Neural Architecture for Hardware Solution to the Assignment Problem’,Neural Networks 4, pp. 431–442.

    Google Scholar 

  • Eberhart, R. C. and Dobbins, R. W. (1990),Neural Network PC Tools, Academic Press, San Diego.

    Google Scholar 

  • Fahlman, S. E. and Lebiere, C. (1990), ‘The Cascade Correlation Learning Architecture’,Advances in Neural Information Processing Systems 2 (D. S. Touretzky, ed.), Morgan Kaufmann, New York, pp. 524–532.

    Google Scholar 

  • Fu, L.-M. and Fu, L.-C. (1990), ‘Mapping Rule-Based Systems into Neural Architecture’,Knowledge Based Systems 3, pp. 48–56.

    Google Scholar 

  • Funahashi, K.-I. (1989) ‘On the Approximate Realization of Continuous Mappings by Neural Networks’,Neural Networks 2, pp. 183–192.

    Google Scholar 

  • Gallant, S. I. (1988), ‘Connectionist Expert Systems’,Communications of the Association for Computing Machinery 24, pp. 152–169.

    Google Scholar 

  • Giarratano, J. and Riley, G. (1989),Expert Systems: Principles and Practice, PWS-KENT, Boston.

    Google Scholar 

  • Hall, L. O. and Romaniuk, S. G. (1990), ‘FUZZNET: Toward a Fuzzy Connectionist Expert System Development Tool’,Proceedings IJCNN 90 (Washington, DC), Vol. II, pp. 483–486.

  • Hertz, J., Krogh, A., and Palmer, R. G. (1991),Introduction to the Theory of Neural Computation, Addison-Wesley, New York.

    Google Scholar 

  • Hirsch, M. W. (1989), ‘Convergent Activation Dynamics in Continuous Time Networks’,Neural Networks 2, pp. 331–349.

    Google Scholar 

  • Hruska, S. I. and Kuncicky, D. C. (1991), ‘Application of Two-Stage Learning to an Expert Network for Control Chart Selection’,Intelligent Engineering Systems Through Artificial Neural Networks (C. Dagli, S. Kumara, and Y. Shin, eds.), ASME Press, New York, pp. 915–920.

    Google Scholar 

  • Kosko, B. (1992),Neural Networks and Fuzzy Systems, Prentice-Hall, Englewood Cliffs, NJ.

    Google Scholar 

  • Kuncicky, D. C. (1990), ‘The Transmission of Knowledge between Neural Networks and Expert Systems’,WNN-AIND 91 (Proceedings of the First Workshop on Neural Networks, Auburn University), pp. 311–319.

  • Kuncicky, D. C. (1991),Isomorphism of Reasoning Systems with Applications to Autonomous Knowledge Acquisition. Ph.D. Dissertation (R. C. Lacher, Major Professor), Florida State University, Tallahassee, FL.

    Google Scholar 

  • Kuncicky, D. C., Hruska, S. I., and Lacher, R. C. (1991), ‘Shaping the Behavior of Neural Networks’,WNN-AIND 91 (Proceedings of the Second Workshop on Neural Networks, Auburn University),SPIE Volume 1515, pp. 173–180.

  • Kuncicky, D. C., Hruska, S. I., and Lacher, R. C. (1992), ‘Hybrid Systems: The Equivalence of Expert System and Neural Network Inference’,International Journal of Expert Systems, to appear.

  • Lacher, R. C., Hruska, S. I., and Kuncicky, D. C. (1991), ‘Expert Networks: a Neural Network Connection to Symbolic Reasoning Systems’,Proceedings FLAIRS 91 (M. B. Fishman, ed.), Florida AI Research Society, St. Petersburg, FL, pp. 12–16.

    Google Scholar 

  • Lacher, R. C., Hruska, S. I., and Kuncicky, D. C. (1992), ‘Backpropagation Learning in Expert Networks’,IEEE Transactions on Neural Networks 3, pp. 62–72.

    Google Scholar 

  • Lacher, R. C. (1992a), ‘Node Error Assignment in Expert Networks’,Hybrid Architectures for Intelligent Systems (A. Kandel and G. Langholz, ed), CRC Press, London, pp. 29–48.

    Google Scholar 

  • Lacher, R.C. (1992b), ‘The Symbolic/Sub-Symbolic Interface: Hierarchical Network Organizations for Reasoning’,Integrating Neural and Symbolic Processes (AAAI-92 Workshop, R. Sun, ed.), July, 1992.

  • Nguyen, K. D., Gibbs, K. S., Lacher, R. C., and Hruska S. I. (1992), ‘A Connection Machine Based Knowledge Refinement Tool’,FLAIRS 92 (M. B. Fishman, ed.), Florida Artificial Intelligence Research Symposium, St. Petersburg, pp. 283–286.

  • Rocker, R. R. (1991),An Eyent-Driven Approach to Artificial Neural Networks Masters Thesis (S. I. Hruska, Major Professor), Florida State University, Tallahassee, FL.

    Google Scholar 

  • Rumelhart, D. E. and McClelland, J. L. (1986),Parallel Distributed Processing, MIT Press, Cambridge, MA.

    Google Scholar 

  • Searle, J.R. (1990), ‘Is the Brain's Mind a Computer Program?’,Scientific American 262, pp. 26–31.

    Google Scholar 

  • Shortliffe, E. H. (1976),Computer-Based Medical Consultations: MYCIN, Elsevier, New York.

    Google Scholar 

  • Shortliffe, E. H. and Buchanan, B. G. (1985), ‘A Model of Inexact Reasoning in Medicine’,Rule-Based Expert Systems, Addison-Wesley, New York, pp. 233–262.

    Google Scholar 

  • Towell, G. G., Shavlik, J. W., and Noordewier, M. O. (1990), ‘Refinement of Approximate Domain Theories by Knowledge-Based Neural Networks’,Proceedings AAAI-90, Morgan Kaufmann, New York, pp. 861–866.

    Google Scholar 

  • Werbos, P. (1974),Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences, Ph.D. Thesis, Harvard University, Cambridge, MA.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, Florida State University, Mail Code B-173, 32306, Tallahassee, FL, USA

    R. C. Lacher

Authors
  1. R. C. Lacher
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

Paper given to the symposiumApproaches to Cognition, the fifteenth annual Symposium in Philosophy held at the University of North Carolina, Greensboro, April 5–7, 1991.

Research partially supported by the US Office of Naval Research and the Florida High Technology and Industry Council.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Lacher, R.C. Expert networks: Paradigmatic conflict, technological rapproachement. Mind Mach 3, 53–71 (1993). https://doi.org/10.1007/BF00974305

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00974305

Key words

Search

Navigation