Abstract | ||
---|---|---|
In this paper, three existing chaotic neural network models are reviewed and the searching ability of these models is analyzed, a novel chaotic neural network with varying initial value is proposed to solve problems of the lower convergence rate and long searching time in the existing method. It is different from the other modified chaotic neural networks in the aspect that it seeks the better initial value that can lead to the global optimized solution in limited steps by means of chaotic iteration instead of enlarging the annealing time or modifying annealing parameters. The new method can get the increasing convergence rate and the decreasing searching time. The controlled numerical experiments with the Travel Salesman Problems (TSP) show that the proposed method has better global searching ability. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1007/11816157_6 | ICIC (1) |
Keywords | Field | DocType |
existing chaotic neural network,annealing time,annealing parameter,existing method,initial value,new method,novel chaotic neural network,modified chaotic neural network,chaotic iteration,global optimization,traveling salesman problem,convergence rate | Computer science,Travelling salesman problem,Artificial intelligence,Rate of convergence,Initial value problem,Artificial neural network,Chaotic,Chaotic neural network | Conference |
Volume | ISSN | ISBN |
4113 | 0302-9743 | 3-540-37271-7 |
Citations | PageRank | References |
0 | 0.34 | 2 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hai-Peng Ren | 1 | 26 | 5.41 |
Lingjuan Chen | 2 | 0 | 0.34 |
Fucai Qian | 3 | 42 | 9.27 |
Chongzhao Han | 4 | 446 | 71.68 |