• DocumentCode
    381196
  • Title

    A new method of improving Wang and Smith´s chaotic neural network

  • Author

    Zheng, Liying ; Wang, Kejun ; Kai Tian

  • Author_Institution
    Autom. Coll., Harbin Eng. Univ., China
  • Volume
    3
  • fYear
    2002
  • fDate
    2002
  • Firstpage
    1994
  • Abstract
    In this paper, a novel method is proposed, with the aid of which the change of time step, Δt, depends on two parameters according to the value of the cost function of combinatorial optimization problems. We have applied Wang and Smith´s (1998) method and the proposed method to 10 city traveling salesman problem (TSP), respectively. The simulation results show that the performance of the proposed method is better than that of Wang and Smith´s chaotic neural networks.
  • Keywords
    bifurcation; chaos; neural nets; simulated annealing; travelling salesman problems; bifurcation; chaotic neural network; chaotic simulated annealing; combinatorial optimization; cost function; performance; simulation; time step; traveling salesman problem; Bifurcation; Cellular neural networks; Chaos; Cities and towns; Cost function; Hopfield neural networks; Neural networks; Optimization methods; Simulated annealing; Traveling salesman problems;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Control and Automation, 2002. Proceedings of the 4th World Congress on
  • Print_ISBN
    0-7803-7268-9
  • Type

    conf

  • DOI
    10.1109/WCICA.2002.1021434
  • Filename
    1021434