Journal of Computer Science and Technology

, Volume 6, Issue 4, pp 305–315 | Cite as

Competition based neural networks for assignment problems

  • Li Tao 
  • Luyuan Fang
Regular Papers


Competition based neural networks have been used to solve the generalized assignment problem and the quadratic assignment problem. Both problems are very difficult and are ε approximation complete. The neural network approach has yielded highly competitive performance and good performance for the quadratic assignment problem. These neural networks are guaranteed to produce feasible solutions.


Neural Network Feasible Solution Energy Function Assignment Problem Combinatorial Optimization Problem 
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]
    S. Abe, Theories on the Hopfield Neural Networks Int. Joint Conf. Neural Network, Vol.1 (June 1989) Washington D. C., 557–564.CrossRefGoogle Scholar
  2. [2]
    P. Bourret, S. Goodall and M. Samuelides, Optimal Scheduling by Competitive Activation: Application to the Satellite Antennae Scheduling Problem. Int, Joint Conf. Neural Networks, Vol.1 (June 1989) Washington D. C., 565–572.CrossRefGoogle Scholar
  3. [3]
    M. Cohen and S. Grossberg, Absolute stability of global pattern formation and parallel memory storage by competitive neural networks.IEEE Trans. Systems, Man and Cybernetics., SMC-13 (Sep./Oct. 1983), 815–826.MATHMathSciNetGoogle Scholar
  4. [4]
    L-Y. Fang, Design of Computational Neural Networks. Ph. D. thesis submitted to the Flinders University of South Australia, March 1990.Google Scholar
  5. [5]
    J. J. Hopfield, Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. USA, Vol.79 (April 1982), 2553–2558.CrossRefMathSciNetGoogle Scholar
  6. [6]
    J. J. Hopfield, Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Natl. Acad. Sci. USA, Vol.81 (May 1984), 3088–3092.CrossRefGoogle Scholar
  7. [7]
    J. J. Hopfield and D. W. Tank, ‘Neural’, computation of decisions in optimization problems.Biological Cybernetics,52 (1985), 141–152.MATHMathSciNetGoogle Scholar
  8. [8]
    J. J. Hopfield and D. W. Tank, Computing with neural circuits: A model.Science,233: 4767 (Aug. 1986) 625–633.CrossRefGoogle Scholar
  9. [9]
    Sahni, S. and Gonzalez, T., P-Complete approximation problems.Journal of the Association for Computing Machinery,23: 3 (1976), 555–565.MATHMathSciNetGoogle Scholar
  10. [10]
    A. B. Kahng, Traveling Salesman Heuristics and Embedding Dimension in the Hopfield Model, Int. Joint Conf. Neural Networks, Vol.1 (June 1989) Washington D.C. 513–520.CrossRefGoogle Scholar
  11. [11]
    Y. Peng, A Connectionist Solution for Vertex Cover Problems. Int. Joint Conf. Neural Networks, Vol.2, (June 1989) Washington D. C., 590.CrossRefGoogle Scholar
  12. [12]
    Y. Peng and J. Reggia, A connectionist model for diagnostic problem solving.IEEE Trans. Syst. Man and Cybernetics, SMC-19 (1989).Google Scholar
  13. [13]
    C. Peterson and J. R. Anderson, Neural Networks and NP-Complete Optimization Problems: A Performance Study on the Graph Bisection Problem. Complex Systems2 (1988), 59.MATHMathSciNetGoogle Scholar
  14. [14]
    C. Peterson and B. Soderberg, A new method for mapping optimization problems onto neural networks.Int. Journal of Neural Systems,1: 1 (1989), 3–22.CrossRefGoogle Scholar
  15. [15]
    J. Reggia, Methods for deriving competitive activation mechanisms. Int Joint Conf. Neural Networks, (June 1989) Washington D. C., 357–363.Google Scholar
  16. [16]
    J. Reggia and G. Sutton, Self-Processing Networks and Their Biomedical Implications. Proc. of IEEE, Vol.76 (1988) 680–692.CrossRefGoogle Scholar
  17. [17]
    D. W. Tank and J. J. Hopfield, Simple ‘Neural’ optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit.IEEE Transactions on Circuit Systems, CAS-33 (May 1986), 533–541.CrossRefGoogle Scholar
  18. [18]
    P. Wang, S. Seidman and J. Reggia, Analysis of competition-based spreading activation in connectionist models.Int. J. Man-Machine Studies,28 (1988), 77–97.CrossRefGoogle Scholar
  19. [19]
    G. V. Wilson and G. S. Pawley, On the Stability of the Traveling Salesman Problem Algorithm of Hopfield and Tank.Biological Cybernetics,58 (1988), 63–70.MATHCrossRefMathSciNetGoogle Scholar
  20. [20]
    D. E. Van den Bout and T. K. Miller, Graph Partitioning Using Annealed Neural Networks. Int. Joint Conf. Neural Networks, Vol.1 (June 1989) Washington D. C., 521–528.CrossRefGoogle Scholar
  21. [21]
    T. Li and L-Y Fang, Parallel approximate solution of 0/1 knapsack optimization on competitive neural network. to appear inAdvances in Parallel Computing, Vol. 3, 1990, North-Holland.Google Scholar

Copyright information

© Science Press, Beijing China and Allerton Press Inc. 1991

Authors and Affiliations

  • Li Tao 
    • 1
  • Luyuan Fang
    • 2
  1. 1.Department of Computer ScienceMonash UniversityClaytonAustralia
  2. 2.Department of Computer ScienceFlinders University of South AustraliaBedford ParkAustralia

Personalised recommendations