A Generic Neural Network Approach For Constraint Satisfaction Problems

  • E. P. K. Tsang
  • C. J. Wang
Part of the Perspectives in Neural Computing book series (PERSPECT.NEURAL)


The Constraint Satisfaction Problem (CSP) is a mathematical abstraction of the problems in many AI application domains. In many of such applications timely response by a CSP solver is so crucial that to achieve it, the user may be willing to sacrifice completeness to a certain extent. This paper describes a neural network approach for solving CSPs which aims at providing prompt responses. The effectiveness of this model, which is called GENET, in solving CSPs with binary constraints is demonstrated by a simulator. Although the completeness is not guaranteed, as in the case of most of the existing stochastic search techniques, solutions have been found by the GENET simulator in all of our randomly generated problems tested so far. Since the neural network model lends itself to the VLSI implementation of parallel processing architectures, the limited number of cycles required by GENET to find the solutions for the tested problems gives hope for solving large CSPs in a fraction of the time required by conventional methods.


Constraint Satisfaction Problem VLSI Implementation Binary Constraint Parallel Processing Architecture Network Convergence 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Waltz, D.L., “Understanding line drawings of scenes with shadows”, in WINSTON, P.H. (ed.) The Psychology of Computer Vision, McGraw-Hill, New York, 1975, 19–91Google Scholar
  2. [2]
    Tsang, E.P.K., “The consistent labelling problem in temporal reasoning”, Proc. AAAI Conference, Seattle, July, 1987, 251–255Google Scholar
  3. [3]
    Dechter, R., Meiri, I. and Pearl, J., “Temporal constraint networks”, Artificial Intelligence, 49, 1991, 61–95CrossRefzbMATHMathSciNetGoogle Scholar
  4. [4]
    Stefik, M., “Planning with Constraints (MOLGEN: part 1)”, Artificial Intelligence 16, 1981, 111–140CrossRefGoogle Scholar
  5. [5]
    Prosser, P., “Distributed asynchronous scheduling”, PhD Thesis, Department of Computer Science, University of Strathclyde, November, 1990Google Scholar
  6. [6]
    Mackworth, A.K., “Consistency in networks or relations”, Artificial Intelligence 8 (1), 1977, 99–118CrossRefzbMATHMathSciNetGoogle Scholar
  7. [7]
    Haralick, R.M. and Elliott, G.L., “Increasing tree search efficiency for constraint satisfaction problems”, Artificial Intelligence 14 (1980), 263–313CrossRefGoogle Scholar
  8. [8]
    Dincbas, M., Simonis, H. and Van Hentenryck, P., “Solving car sequencing problem in constraint logic programming”, Proceedings, European Conference on AI, 1988, 290–295Google Scholar
  9. [9]
    Dincbas, M., Van Hentenryck, P., Simons, H., Aggoun, A. and Graf, T., “Applications of CHIP to industrial and engineering problems”, First International Conference on Industrial and Engineering Applications of AI and Expert Systems, June, 1988Google Scholar
  10. [10]
    Perrett, M., “Using Constraint Logic Programming Techniques in Container Port Planning”, ICL Technical Journal, May 1991Google Scholar
  11. [11]
    Saletore, V.A. and Kale, L.V., “Consistent linear speedups to a first solution in parallel state-space search”, Proc. AAAI, 1990, 227–233Google Scholar
  12. [12]
    Kasif, S., “On the parallel complexity of discrete relaxation in constraint satisfaction networks”, Artificial Intelligence (45) 1990, 275–286CrossRefzbMATHMathSciNetGoogle Scholar
  13. [13]
    Hopfield, J. J., and Tank, D.W., ‘Neural’ Computation of Decisions in Optimization Problems“, Biol. Cybern. (52) 1985, 141–152zbMATHMathSciNetGoogle Scholar
  14. [14]
    Adorf, H.M. and Johnston, M.D., “A discrete stochastic neural network algorithm for constraint satisfaction problems”, Proceedings, International Joint Conference on Neural Networks, 1990Google Scholar
  15. [15]
    Minton, S., Johnston, M.D., Philips, A. B. and Laird, P., “Solving large-scale constraint-satisfaction and scheduling problems using a heuristic repair method”, Proc. AAAI, 1990, 17–24Google Scholar
  16. [16]
    Swain, M.J. and Cooper, P.R., “Parallel hardware for constraint satisfaction”, Proc. AAAI, 1988, 682–686Google Scholar
  17. [17]
    Cooper, P., “Structure recognition by connectionist relaxation: formal analysis”, Proc. Canadian AI Conference (CSCSI), 1988, 148–155Google Scholar
  18. [18]
    Guesgen, H.W., “Connectionist networks for constraint satisfaction”, AAAI Spring Symposium on Constraint-based Reasoning, March, 1991, 182–190Google Scholar
  19. [19]
    Collin Z., Dechter, R. and Katz, S., “On the Feasibility of distributed constraint satisfaction”, Proc. International Joint Conference on AI, 1991, 318–324Google Scholar
  20. [20]
    Wang, C. J., and Tsang, E. T. K., “Solving constraint satisfaction problems using neural networks”, Proc. TEE Second International Conference on Artificial Neural Networks, 1991Google Scholar
  21. [21]
    Davis, L. (ed.), “Genetic algorithms and simulated annealing”, Research notes in AI, Pitman/Morgan Kaufmann, 1987zbMATHGoogle Scholar
  22. [22]
    Wang, C.J., “A cascadable parallel architecture for GENET”, Research Notes, Department of Computer Science, University of Essex, forthcoming.Google Scholar
  23. [23]
    Freuder, E.C., “Partial constraint satisfaction”, Proc., 11th International Joint Conference on AI, 1989, 278–283Google Scholar
  24. [24]
    Parrello, B.D., Kabat, W.C. and Wos, L., “Job-shop scheduling using automated reasoning: a case study of the car sequencing problem”, Journal of Automatic Reasoning, 2 (1), 1986, 1–42MathSciNetGoogle Scholar

Copyright information

© Springer-Verlag London Limited 1992

Authors and Affiliations

  • E. P. K. Tsang
    • 1
  • C. J. Wang
    • 1
  1. 1.Department of Computer ScienceUniversity of EssexColchesterUK

Personalised recommendations