Abstract
Recently the relation of subsymbolic (“neural computing”) and symbolic computing has been a topic of intense discussion. Our purpose is to focus this discussion to the particular application area of expert system design. We address some of the drawbacks of current expert systems and study the possibility of using neural computing methodologies to improve their competence. The topic can be discussed at various levels of integration: the higher the integration level, the more symbolic functionalities (such as an inference engine) are implemented directly at the level of the neural computational model.
In this paper we address the lowest levels of integration: neural networks that can be used to implement feature recognizers which allow symbolic inference engines to make direct use of complex sensory input via so called detector predicates. We also introduce the notion of self organization as a means to determine those attributes (properties) of data that reflect meaningful statistical relationships in the expert system input space, thus addressing the difficult problem of conceptual clustering (“abstraction”) of information. The concepts introduced are illustrated by two examples: an automatic inspection system for circuit packs and an expert system for respiratory and anesthesia monitoring. The adopted approach differs considerably 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 representations at the higher reasoning levels without sacrificing the power of noise-tolerant pattern association (“inference by memory”) offered by neural computing methods.
This research is supported by TEKES through FINSOFT grant. This work was done while the author was visiting AT&T Bell Laboratories.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Anderson,J.A. and E.Rosenfeld (Eds.), Neurocomputing. Foundations of research. The MIT Press, 1988.
Becker, L.E. and J. Peng, Using activation networks for analogical ordering of consideration: one method for integrating connectionistic and symbolic processing. IEEE International Conference on Neural Networks, San Diego, pp.367–371, 1987.
Bounds, D.G, P.J. Lloyd, B. Matthew and G. Waddell, A multi layer perceptron network for the diagnosis of low back pain. IEEE International Conference Neural Networks, San Diego, pp.481–489, 1988.
Callero, M., D.A. Waterman and J. Kipps, TATR: a prototype expert system for tactical air targeting. Rand Report R-3096-ARPA, The Rand Corporation, Santa Monica, CA, 1984.
Davis,R., Diagnostic reasoning based on structure and behaviour. Artificial Intelligence (24), 347–410, 1984.
Duda,R.O. and P.E.Hart, Pattern classification and scene analysis, John wiley & Sons, 1973.
Dutta, S. and S. Shekhar, Bond rating: a non-conservative application of neural networks. IEEE International Conference on Neural Networks, San Diego, pp.443–450, 1988.
Gallant,S.I., Connectionistic expert systems. Communications of the ACM (31), pp. 152–169, 1988.
Grossberg,S.(Ed.), Neural networks and natural intelligence. The MIT Press, 1988.
Hecht-Nielsen,R., Neurocomputer applications. In R.Eckmiller and C.v.d.Malsburg (Eds.), Neural computers, Springer-Verlag, pp. 445–451, 1987.
Hecht-Nielsen,R., Counterpropagation networks. To appear in Applied Optics, 1987.
Kandel,E.R. and J.H.Schwartz, Principles of neural science, Elsevier, 1985.
Keravnou,E.T. and L.Johnson, competent expert systems — a case study in fault diagnosis. McGraw-Hill, 1986.
Kohonen,T., Self-organization and associative memory. 2nd Edition. Springer-Verlag, 1988.
Lippmann,R.P., An introduction to computing with neural nets. IEEE ASSP Magazine, pp. 4–22, 1987.
Morris,R.J.T.,L.Rubin and H.Tirri, A computer vision system for font orientation detection: solution by optimal detection and learning vector quantization approaches. In preparation, preprint available from authors, 1989.
Morris,R.J.T.,L.Rubin and H.Tirri, A comparison of feedforward and self-organizing approaches to the font orientation problem. To appear in IJCNN'89, 1989.
Nelson, W.R., REACTOR: an expert system for diagnosis and treatment of nuclear reactor accidents. Proceedings of AAAI, 1982.
Quinlan,R., Discovering rules from large collections of examples. A case study. In D.Mitchie (ed.), Expert systems in the microelectronic age. Edinburgh University Press, 1979.
Rader, C.D., V.M. Crowe and B.G. Marcot, 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.
Rumelhart,D.E. and J.L. McClelland (Eds.), Parallel distributed processing: explorations in the microstructures of cognition. Vol 1,2. The MIT Press, 1986.
Wallis, J.W. and E.H. Shortliffe,Explanatory power for medical expert systems: studies in the representation of causal relationships for clinical consultations. Meth. Inform. Med (21), pp.127–136, 1982.
Waterman,D.A., A guide to expert systems. Addison-Wesley, 1986.
Weiss, S.M. and C.A. Kulikowski, A practical guide to designing expert systems. Rowman&allanheld (NJ,USA), 1984.
Werbos,P., Beyond regression: new tools for prediction and analysis in the behavioral sciences. Ph.D. thesis, Harvard U. Committee on applied Mathematics, 1974.
Werbos, P., Backpropagation: past and future. IEEE International Conference on Neural Networks, San Diego, pp.343–353, 1988.
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.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1989 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tirri, H. (1989). Applying neural computing to expert system design: Coping with complex sensory data and attribute selection. In: Litwin, W., Schek, HJ. (eds) Foundations of Data Organization and Algorithms. FODO 1989. Lecture Notes in Computer Science, vol 367. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-51295-0_149
Download citation
DOI: https://doi.org/10.1007/3-540-51295-0_149
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-51295-0
Online ISBN: 978-3-540-46186-9
eBook Packages: Springer Book Archive