• DocumentCode
    2988091
  • Title

    Comparison of the Hopfield scheme to the hybrid of Lagrange and transformation approaches for solving the traveling salesman problem

  • Author

    Lau, K.M. ; Chan, S.M. ; Xu, L.

  • Author_Institution
    Dept. of Comput. Sci., Chinese Univ. of Hong Kong, Shatin, Hong Kong
  • fYear
    1995
  • fDate
    29-31 May 1995
  • Firstpage
    209
  • Lastpage
    216
  • Abstract
    A novel scheme, the hybrid of Lagrange and transformation approaches (Hybrid LT), was proposed by Xu (1994) to solve a combinatorial optimization problem. It separates the constraints into linear-constant-sum constraints and binary constraints. The linear-constant-sum constraints are treated by the Lagrange approach while the binary constraints are transformed into penalty or barrier functions. This paper compares the performance of the Hopfield net and the Hybrid LT based on computer simulations in solving the traveling salesman problem (TSP). The experimental results show that the Hybrid LT is superior to the Hopfield net for greater speed of convergence, higher rate of finding valid solutions and shorter paths found
  • Keywords
    Hopfield neural nets; combinatorial mathematics; mathematics computing; optimisation; travelling salesman problems; Hopfield net; Lagrange; binary constraints; combinatorial optimization; computer simulations; linear-constant-sum constraints; transformation approaches; traveling salesman problem; Cities and towns; Computer science; Constraint optimization; Convergence; Hopfield neural networks; Hybrid power systems; Lagrangian functions; Neural networks; Neurons; Traveling salesman problems;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligence in Neural and Biological Systems, 1995. INBS'95, Proceedings., First International Symposium on
  • Conference_Location
    Herndon, VA
  • Print_ISBN
    0-8186-7116-5
  • Type

    conf

  • DOI
    10.1109/INBS.1995.404259
  • Filename
    404259