This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Connectionist Expert System with Adaptive Learning Capability
June 1991 (vol. 3 no. 2)
pp. 200-207

A neural network expert system called adaptive connectionist expert system (ACES) which will learn adaptively from past experience is described. ACES is based on the neural logic network, which is capable of doing both pattern processing and logical inferencing. The authors discuss two strategies, pattern matching ACES and rule inferencing ACES. The pattern matching ACES makes use of past examples to construct its neural logic network and fine-tunes itself adaptively during its use by further examples supplied. The rule inferencing ACES conceptualizes new rules based on the frequencies of use on the rule-based neural logic network. A new rule could be considered as a pattern matching example and be incorporated into pattern matching ACES.

[1] W. G. Chase and H. A. Simon, "The mind's eye in chess" inVisual Information Processing. W. G. Chase, Ed. New York: Academic, 1973.
[2] J. Larkin, J. McDermott, D. P. Simon, and H. A. Simon, "Expert and novice performance in solving physics problems,"Science, vol. 208, pp. 1335-1342, 1980.
[3] A. G. Bateson, R. A. Alexander, and M. D. Murphy, "Cognitive processing differences between novice and expert computer programmers,"Int. J. Man-Machine Studies. vol. 26, pp. 649-660, 1987.
[4] J. R. Anderson,Cognitive Psychology and Its Applications, 2nd ed., San Fransico, CA, Freeman, 1985.
[5] A. H. Tan and L. K. Chee, "Connectionist expert system for intelligence advisory application," inProc. Expert Syst. Econom. Banking, Management, and Singapore, Jan 11-13, 1989.
[6] K. Saito and R. Nakano, "Medical diagnostic expert system based on PDP model," inProc. IEEE ICNN, Vol. II, San Diego, CA, July 24-27, 1988, pp. 525-532.
[7] G. Bradshaw, R. Fozzard, and L. Ceci, "A connectionist expert system that actually works,"Advances Neural Inform. Processing Syst., 1, pp. 248-255.
[8] S. I. Gallant, "Connectionist expert systems,"Commun. ACM, vol. 31, no. 2, pp. 152-169, Feb. 1988.
[9] S. I. Gallant, "Automatic generation of expert system from examples," inProc. 2nd Int. Conf. AI Appl., IEEE Press, New York, 1985, pp. 313-319.
[10] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning internal representation by error propagation,"Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vols. 1 and 2. Cambridge, MA: MIT Press, 1986.
[11] T. J. Sejnowski and C. R. Rosenbert, "Parallel networks that learn to pronounce English text,"Complex Syst., vol. 1, pp. 145-168, 1987.
[12] H. H. Teh and C. P. Yu Wellington, "A controlled learning environment of enhanced perceptron," inIEEE Proc., Future Trend in Distributed Comput. Syst., 1988, Hong Kong.
[13] S.C. Chan, L.S. Hsu, S. Brody, and H.H. Teh, "Neural three-valued-logic networks," inProc., Inter-Faculty Seminar Neuronet Comput., June 1989, National Univ. of Singapore, pp. 54-75.
[14] A. H. Tan, Q. Pan, H.C. Lui, and H. H. Teh, "INSIDE: A neuronet based hardware fault diagnostic system," inProc. Int. Joint Conf. Neural Networks, San Diego, CA, June 17-21, 1990.
[15] A. H. Tan and H. H. Teh, "Connectionist expert systems--An inductive cum deductive approach,"Inform Technol.--J. Singapore Comput. Society, Special Issue on Knowledge Engineering, Feb. 1990.
[16] H. H. Teh, S. C. Chan, L. S. Hsu, and K. F. Loe, "Probabilistic neural-logic networks," inProc. Inter-Faculty Neuronet Seminar, National Univ. of Singapore, June 1989.
[17] L. S. Hsu, H. H. Teh, S. C. Chan, and K. F. Loe, "Fuzzy decision making based on neural-logic networks," inProc. Inter-Faculty Neuronet Seminar, National Univ. of Singapore, June 1989.
[18] T. Samad, "Towards connectionist rule-based systems," inProc. IEEE Int. Conf. Neural Networks, 1988.
[19] H. H. Teh, L. S. Hsu, and W. W. Tsang, "Modelling knowledge information systems using inference networks,"ARS Combinatoria, vol. 23A, pp. 269-290, 1987.
[20] T.J. Reynolds, H.H. Teh, and B.T. Low, "Programming in neural logic,"Pacific Rim Int. Conf. AI'90, Nov. 14-16, Nagoya, Japan.
[21] C. Anderson and E. Abrahams, "The Bayes connection," inProc. IEEE Int. Conf. Neural Networks, San Diego, CA, 1987, pp. III105-112.
[22] L. Becker and J. Peng, "Networking processing of hierarchical knowledge for classification and diagnosis," inProc. IEEE Int. Conf. Neural Networks, San Diego, CA, 1987, pp. II309-317.
[23] S. Chan, "Automated reasoning on neural networks: A probabilistic approach," inProc. IEEE Int. Conf. Neural Networks, San Diego, CA, 1987, pp. II373-378.
[24] J.R. Quinlan, "Generating production rules from decision trees," inProc. IJCAI 87, Milan, pp. 304-307.

Index Terms:
adaptive learning capability; neural network expert system; adaptive connectionist expert system; past experience; neural logic network; pattern processing; logical inferencing; pattern matching ACES; rule inferencing ACES; past examples; neural logic network; adaptive systems; expert systems; inference mechanisms; neural nets; pattern recognition
Citation:
B.T. Low, H.C. Lui, A.H. Tan, H.H. Teh, "Connectionist Expert System with Adaptive Learning Capability," IEEE Transactions on Knowledge and Data Engineering, vol. 3, no. 2, pp. 200-207, June 1991, doi:10.1109/69.88000
Usage of this product signifies your acceptance of the Terms of Use.