This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Representing Knowledge by Neural Networks for Qualitative Analysis and Reasoning
October 1995 (vol. 7 no. 5)
pp. 683-690

Abstract—A systematic approach has been developed to construct neural networks for qualitative analysis and reasoning. These neural networks are used as specialized parallel distributed processors for solving constraint satisfaction problems. A typical application of such a neural network is to determine a reasonable change of a system after one or more of its variables are changed. A six-node neural network is developed to represent fundamental qualitative relations. A larger neural network can be constructed hierarchically for a system to be modeled by using six-node neural networks as building blocks. The complexity of the neural network building process is thus kept manageable. An example of developing a neural network reasoning model for a transistor equivalent circuit is demonstrated. The use of this neural network model in the equivalent circuit parameter extraction process is also described.

[1] P.J. Hayes,“Naive physics manifesto,” Expert Systems in the Microelectronics Age, D. Michie, ed. Edinburgh: Edinburgh Univ. Press, 1979.
[2] D.G. Bobrow,“Qualitative reasoning about physical systems: An introduction,” Artificial Intelligence, vol. 24, pp. 1-5, 1984.
[3] P.A. Fishwick,“Qualitative simulation: Fundamental concepts and issues,” Proc. 1988 AI and Simulation Conf., pp. 25-31.
[4] R. Rajagopalan,“Qualitative modeling and simulation: A survey,” AI Applied to Simulation, E.J.H. Kerckhoffs, G.C. Vansteenkiste, and B.P. Zeigler, eds., Soc. for Computer Simulation, pp. 9-30, 1986.
[5] Y. Iwasaki,“Qualitative physics,” The Handbook of Artificial Intelligence, A. Barr, P.R. Cohen, and E.A. Feigenbaum, eds. Reading, Mass.: Addison-Wesley, vol. IV, pp. 323-413, 1989.
[6] B.C. Williams,“Qualitative analysis of MOS Circuits,” Artificial Intelligence, vol. 24, pp. 281-346, 1984.
[7] J. de Kleer,“How circuits work,” Artificial Intelligence, vol. 24, pp. 205-280, 1984.
[8] R.M. Stallman and G.J. Sussman,“Forward reasoning and dependency-directed backtracking in a system forcomputer-aided circuit analysis,” Artificial Intelligence, vol. 9, pp. 135-196, 1977.
[9] A.K. Mackworth,“Constraint satisfaction,” Encyclopedia of Artificial Intelligence, S.C. Shapiro, ed., vol. 1. New York: John Wiley and Sons, pp. 285-293, 1992.
[10] M.S. Riley and P. Smolensky,“A parallel model of (sequential) problem solving,” Proc. Sixth Ann. Conf. Cognitive Science Soc., pp. 286-292, 1984.
[11] V. Ajjanagadde and L. Shastri,“Rules and variables in neural nets,” Neural Computation, vol. 3, pp. 121-134, 1991.
[12] T. Lange and M. Dyer,“High-level inferencing in a connectionist network,” Connection Science, vol. 1, no. 2, pp. 181-217, 1989
[13] G.E. Hinton,T.J. Sejnowski,, and D.H. Ackley,Boltzmann Machines: Constraint Satisfaction Networks that Learn, Technical Report CMU-CS-84-119, Dept. of Computer Science, Carnegie Mellon Univ., Pittsburgh, 1984.
[14] J.J. Hopfield,“Neural networks and systems with emergent collective computationalabilities,” Proc. Nat’l Academy of Science U.S.A., vol. 79, pp. 2,554-2,558, 1982.
[15] J.J. Hopfield,“Neurons with graded response have collective computational propertieslike those of two-state neurons,” Proc. Nat’l Academy of Science U.S.A, vol. 81, pp. 3,088-3,092, 1984.
[16] J.J. Hopfield and D.W. Tank,“Neural composition of decisions optimization problems,” Biological Cybernetics, vol. 55, pp. 141-152, 1985.
[17] G.V. Wilson and G.S. Pawley, "On the Stability of the Travelling Salesman Problem Algorithm of Hopfield and Tank," Biological Cybernetics, vol. 58, pp. 63-70, 1988.
[18] M. Vai,S. Prasad,N.C. Li,, and F. Kai,“Modeling of microwave semiconductor devices using simulated annealingoptimization,” IEEE Trans. Electron Devices, vol. 36, pp. 761-762, 1989.
[19] S. Kirkpatrick,C.D. Gelatt Jr.,, and M.P. Vecchi,“Optimization by simulated annealing,” Science, vol. 220, pp. 671-680, May 1983.
[20] W.J. McCalla, Fundamentals of Computer-Aided Circuit Simulation, Kluwer Academic, 1988.
[21] W.A. Fisher,R.J. Fujimoto,, and R.C. Smithson,“A programmable analog neural network processor,” IEEE Trans. Neural Networks, vol. 2, no. 2, pp. 222-220, 1991.
[22] W. Lin, V.K. Prasanna, and K.W. Przytula, "Algorithmic Mapping of Neural Network Models onto Parallel SIMD Machines," IEEE Trans. Computers, vol. 40, no. 12, pp. 1,390-1,401, Dec. 1991.

Index Terms:
Knowledge representation, qualitative reasoning, constraint satisfaction, parallel distributed processing, neural networks, expert systems.
Citation:
Mankuan Vai, Zhimin Xu, "Representing Knowledge by Neural Networks for Qualitative Analysis and Reasoning," IEEE Transactions on Knowledge and Data Engineering, vol. 7, no. 5, pp. 683-690, Oct. 1995, doi:10.1109/69.469828
Usage of this product signifies your acceptance of the Terms of Use.