Skip to main content
SpringerLink
Log in

Implementing expert system rule conditions by neural networks

  • Regular Papers
  • Published:
New Generation Computing Aims and scope Submit manuscript

Abstract

The relation of subsymbolic (neural computing) and symbolic computing has been a topic of intense discussion. We address some of the drawbacks of current expert system technology and study the possibility of using neural computing principles to improve their competence. In this paper we focus on the problem of using neural networks to implement expert system rule conditions. Our approach allows symbolic inference engines to make direct use of complex sensory input via so called detector predicates. We also discuss the use of self organizing Kohonen networks as a means to determine those attributes (properties) of data that reflect meaningful statistical relationships in the expert system input space. This mechanism can be used to address the defficult problem of conceptual clustering of information. The concepts introduced are illustrated by two application examples: an automatic inspection system for circuit packs and an expert system for respiratory and anesthesia monitoring. The adopted approach differs from the earlier research on the use of neural networks as expert systems, where the only method to obtain knowledge is learning from training data. In our approach the synergy of rules and detector predicates combines the advantages of both worlds: it maintains the clarity of the rule-based knowledge representation at the higher reasoning levels without sacrificing the power of noise-tolerant pattern association offered by neural computing methods.

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

  1. Anderson, J. A. and Rosenfeld, E. (eds.),Neurocomputing. Foundations of Research, MIT Press, 1988.

  2. Becker, L. E. and Peng, J., “Using Activation Networks for Analogical Ordering of Consideration: One Method for Integrating Connectionistic and Symbolic Processing,”Proceedings of the IEEE International Conference on Neural Networks, San Diego, pp. 367–371, 1987.

  3. Bounds, D. G., Lloyd, P. J., Matthew, B. and Waddell, G., “A Multi Layer Perceptron Network for the Diagnosis of Low Back Pain,”Proceedings of the IEEE International Conference on Neural Networks, San Diego, pp. 481–489, 1988.

  4. Brousse, O. and Smolensky, P., “Virtual Memories and Massive Generalization in Connectionist Combinatorial Learning,”Report, CS-431-89, Department of Computer Science, University of Colorado at Boulder, 1989.

  5. Callero, M., Waterman, D. A. and Kipps, J., “TATR: A Prototype Expert System for Tactical Air Targeting,”Rand Report, R-3096-ARPA, Rand Corporation, Santa Monica, CA, 1984.

    Google Scholar 

  6. Duda, R. O. and Hart, P. E.,Pattern Classification and Scence Analysis, John Wiley & Sons, 1973.

  7. Dutta, S. and Shekhar, S., “Bodn Rating: A Non-Conservative Application of Neural Networks,”Proceedings of the IEEE International Conference on Neural Networks, San Diego, pp. 443–450, 1988.

  8. Gallant, S. I., “Connectionistic Expert Systems,”Communications of the ACM, 31, pp. 152–169, 1988.

    Article  Google Scholar 

  9. Grossberg, S. (ed.),Neural Networks and Natural Intelligence, MIT Press, 1988.

  10. Hecht-Nielsen, R., “Neurocomputer Applications,” inNeural Computers (R. Eckmiller and C. v. d. Malsburg, eds.), Springer-Verlag, pp. 445–451, 1987.

  11. Hecht-Nielsen, R., “Counterpropagation Networks,” to appear inApplied Optics, 1987.

  12. Kandel, E. R. and Schwartz, J. H.,Principles of Neural Science, Elsevier, 1985.

  13. Keravnou, E. T. and Johnson, L.,Competent Expert Systems—A Case Study in Fault Diagnosis, McGraw-Hill, 1986.

  14. Kohonen, T.,Self-Organization and Associative Memory, 2nd Edition, Springer-Verlag, 1988.

  15. Lippmann, R. P., “An Introduction to Computing with Neural Nets,”IEEE ASSP Magazine, pp. 4–22, 1987.

  16. Lippmann, R. P., Gold, B. and Malpass, M.L., “A Comparison of Hamming and Hopfield Neural Nets for Pattern Classification,”Technical Report, 769, MIT Lincoln Laboratory, MIT, pp. 463–502, 1987. Press, 1969.

  17. McCloskey, M. and Cohen, N., “Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem,” to appear inThe Psychology of Learning and Motivation, Vol 23 (G. Bower, ed.), 1988.

  18. Morris, R. J. T., Rubin, L. and Tirri, H., “Neural Network Techniques for Object Orientation Detection: Solution by Optimal Feedforward Network and Learning Vector Quantization Approaches,”IEEE Trans. on Pattern Analysis and Machine Intelligence, 12, pp. 1107–1115, 1990.

    Article  Google Scholar 

  19. Morris, R. J. T., Rubin, L. and Tirri, H., “A Comparison of Feedforward and Self-Organizing Approaches to the Font Orientation Problem,”Proceedings of the International Joint Conference on Neural Networks (IJCNN’89), Washington D. C., pp. 291–298, 1989.

  20. Nelson, W. R., “REACTOR: An Expert System for Diagnosis and Treatment of Nuclear Reactor Accidents,”Proceedings of AAAI, 1982.

  21. Quinlan, R., “Discovering Rules from Large Collections of Examples. A Case Study,” inExpert Systems in the Microelectronic age (D. Mitchie, ed.), Edinburgh University Press, 1979.

  22. Rader, C. D., Crowe, V. M. and Marcot, B. G., “CAPS: A Pattern Recognition Expert System Prototype for Respiratory and Anesthesia Monitoring,”Proceedings of Western Conference on Expert Systems, Anaheim, CA, pp. 162–168, 1987.

  23. Rumelhart, D. E. and McClelland, J. L. (eds.)Parallel Distributed Processing: Explorations in the Microstructures of Cognition, Vol. 1, 2, MIT Press, 1986.

  24. Steinbuch, K.,Die Lernmatrix. Kybernetik 1, pp. 36–45, 1961.

    Article  Google Scholar 

  25. Steinbuch, K. and Piske, U. A., “Learning Matrices and Their Applications,”IEEE Trans. on Electronic Computers, pp. 846–862, 1963.

  26. Taylor, W., “Cortico-Thalamic Organization and Memory,”Proc. Royal Society of London B 159, pp. 466–478, 1964.

    Article  Google Scholar 

  27. Tirri, H., “Applying Neural Computing to Expert System Design: Coping with Complex Sensory Data and Attribute Selection,”Proceedings of the 3rd International Conference on Foundations of Data Organization and Algorithms (FODO’89), Paris, pp. 474–489, 1989.

  28. Tirri, H.,Sparse and Continuous Random Concepts in Artificial Intelligence, submitted for publication, 1990.

  29. Wallis, J. W. and Shortliffe, E. H., “Explanatory Power for Medical Expert Systems: Studies in the Representation of Causal Relationships for Clinical Consultations,”Meth. Inform. Med., 21, pp. 127–136, 1982.

    Google Scholar 

  30. Waterman, D. A.,A Guide to Expert Systems, Addison-Wesley, 1986.

  31. Weiss, S. M. and Kulikowski, C. A.,A Practical Guide to Designing Expert Systems, Rowman & Allanheld (NJ, USA), 1984.

    Google Scholar 

  32. Werbos, P., “Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences,”Ph. D. thesis, Harvard U. Committee on Applied Mathematics, 1974.

  33. Werbos, P., “Backpropagation: Past and Future,”Proceedings of the IEEE International Conference on Neural Networks, San Diego, pp. 343–353, 1988.

  34. Zadeh, L. A., “The Role of Fuzzy Logic in the Management of Uncertainty in Expert Systems,”Fuzzy Sets and Systems, 11, pp. 199–227, 1983.

    Article  MATH  MathSciNet  Google Scholar 

Download references

Author information

Author notes

  1. Henry Tirri

    Present address: Department of Computer Sciences, Purdue University, 47907, West Lafayette, IN, USA

Authors and Affiliations

  1. Department of Computer Sciences, Purdue University, 47907, West Lafayette, IN, USA

    Henry Tirri

Authors
  1. Henry Tirri
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

This research is supported by Technology Development Center (TEKES) in Software Technology Programme (FINSOFT). Part of this work was done while the author was visiting AT & T Bell Laboratories.

About this article

Cite this article

Tirri, H. Implementing expert system rule conditions by neural networks. New Gener Comput 10, 55–71 (1991). https://doi.org/10.1007/BF03037522

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF03037522

Keywords

Search

Navigation