Neural expert systems

Abstract The advantages and disadvantages of classical rule-based and neural approaches to expert system design are complementary. We propose a strictly neural expert system architecture that enables the creation of the knowledge base automatically, by learning from example inferences. For this purpose, we employ a multilayered neural network, trained with generalized back propagation for interval training patterns, which also makes the learning of patterns with irrelevant inputs and outputs possible. We eliminate the disadvantages of the neural approach by enriching the system with the heuristics to work with incomplete information, and to explain the conclusions. The structure of the expert attributes is optional, and a user of the system can define the types of inputs and outputs (real, integer, scalar type, and set), and the manner of their coding (floating point, binary, and unary codes). We have tested our neural expert system on several nontrivial real-world problems (e.g., the diagnostics and progress prediction of hereditary muscular disease), and the results are very good.

[1]  Carl G. Looney.  Neural networks as expert systems , 1993 .

[2]  Jirí Síma,et al.  Back-propagation is not Efficient , 1996, Neural Networks.

[3]  Stephen I. Gallant,et al.  Connectionist expert systems , 1988, CACM.

[4]  Stephen I. Gallant,et al.  Neural network learning and expert systems , 1993 .

[5]  T. Samad.  Towards connectionist rule-based systems , 1988, IEEE 1988 International Conference on Neural Networks.

[6]  Harris Drucker.  Implementation of minimum error expert system , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[7]  R. Nakano,et al.  Medical diagnostic expert system based on PDP model , 1988, IEEE 1988 International Conference on Neural Networks.

[8]  Giovanni Soda,et al.  An unified approach for integrating explicit knowledge and learning by example in recurrent networks , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[9]  H. Shvaytser.  Even simple neural nets cannot be trained reliably with a polynomial number of examples , 1989, International 1989 Joint Conference on Neural Networks.

[10]  Jirí Síma,et al.  Loading Deep Networks Is Hard , 1994, Neural Comput..

[11]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[12]  Maureen Caudill.  Expert networks , 1990 .

[13]  P. K. M'Pherson,et al.  Second European meeting on cybernetics and systems research: Vienna 16–19 April 1974 Organised by the Austrian Society for Cybernetic Studies , 1974 .

[14]  Naoki Hara,et al.  Fuzzy rule extraction from a multilayered neural network , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[15]  Alan F. Murray.  Applications of Neural Networks , 1994 .

[16]  Ronald L. Rivest,et al.  Training a 3-node neural network is NP-complete , 1988, COLT '88.

[17]  Q. Yang,et al.  Building expert systems by a modified perceptron network with rule-transfer algorithms , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[18]  Stephen I. Gallant.  Automated generation of connectionist expert systems for problems involving noise and redundancy , 1988, Int. J. Approx. Reason..

[19]  J. Stephen Judd,et al.  Neural network design and the complexity of learning , 1990, Neural network modeling and connectionism.

[20]  Susan I. Hruska,et al.  Hybrid learning in expert networks , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[21]  Michael C. Mozer,et al.  Learning explicit rules in a neural network , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[22]  J. J. Gelfand,et al.  Integration of knowledge-based system and neural network techniques for autonomous learning machines , 1989, International 1989 Joint Conference on Neural Networks.

[23]  William G. Baxt,et al.  Use of an Artificial Neural Network for Data Analysis in Clinical Decision-Making: The Diagnosis of Acute Coronary Occlusion , 1990, Neural Computation.