小波混沌神经网络模拟退火参数研究  

Research on simulated annealing parameters in wavelet chaotic neural network

作　　者：徐耀群[1] 岳海燕 

机构地区：[1]哈尔滨商业大学系统工程研究所,哈尔滨150028 [2]哈尔滨工程大学数学系,哈尔滨150001

出　　处：《计算机工程与应用》2008年第2期80-82,189,共4页Computer Engineering and Applications

基　　金：黑龙江省自然科学基金( the Natural Science Foundation of Heilongjiang Province of China under Grant No.F200610);黑龙江省教育厅科学技术项目( No.10541073) 。

摘　　要：小波混沌神经网络已经成功地解决了函数优化和组合优化问题。研究了分段指数退火函数的Morlet小波混沌神经元模型,给出了分段小波混沌神经元的倒分岔图和Lyapunov指数图。在小波混沌神经网络的基础上,加入了分段指数退火函数,提出了一种新的改进的小波混沌神经网络,并把它应用到函数优化和组合优化问题中。仿真结果表明,改善了小波混沌神经网络的寻优能力,改进的小波混沌神经网络优于原来的小波混沌神经网络。Wavelet chaotic neural networks have successfully solved function and combinatorial optimization problems.Morlet wavelet chaotic neural units with the annealing function of subparagraph index are studied.The reversed bifurcation and Lyapunov exponent figures are respectively given.On the basis of wavelet chaotic neural network,the annealing function of subparagraph index is introduced into network,a new reformative wavelet chaotic neural network is presented.Then it is applied to function and combinatorial optimization problems.The simulation results show that the search-optimization capacity of wavelet chaotic neural network has been improved and the reformative wavelet chaotic neural network is superior to the primary wavelet chaotic neural networks.

关 键 词：小波混沌神经网络 LYAPUNOV指数 模拟退火参数 TSP 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]