文档介绍：高斯非线性自反馈混沌神经网络及应用
许楠1 刘丽杰1 徐耀群2
黑龙江八一农垦大学信息技术学院,黑龙江大庆 163319;,哈尔滨 150028)
摘要:基于Chen’s暂态混沌神经网络模型,改变其线性自反馈过程,采用由高斯函数作用的非线性自反馈连接项,通过分析神经元倒分叉图以及Lyapunov指数,研究该新模型的神经元动力学特性。在该神经元模型基础上构建高斯非线性自反馈混沌混沌神经网络,并将其应用于组合优化问题(TSP)中,通过仿真实验,研究主要参数对网络寻优能力的影响,实验结果表明如果参数取值适当,网络具有逃离局部极小点的能力并能够以较高的最优比收敛到平衡点。
关键词:非线性;自反馈;神经元;高斯函数
中图分类号: TP391 文献标识码: A 文章编号:
A Novel Chaotic work with Gaussian Function Self-feedback and Its Application to TSP
XU Nan1 Liu Lijie1 XU Yao-qun2
( of Information Technology, Heilongjiang Bayi Agricultural University, Heilongjiang Daqing, 163319 2. Institute of System Engineering, Harbin University merce, Harbin, 150028)
Abstract: This novel chaotic work bases on the Chen’s transiently chaotic work. The linear Self-feedbak of the Chen’work is changed to Gaussian nonlinear one. The dynamics behavior of the single neuron is researched by analyzing the backward bifurcation diagram and the Lyapunov exponent. A Novel Chaotic work with Gaussian Function Self-feedback is structured on the model of neuron. The work is used to binatorial optimization problem-TSP. The main parameters are researched for the capability of searching optimal path. The simulation result indicates that it can avoid the limit of being trapped into the local minima and converge to the equilibrium point with high optimal proportion.
Key words:Nonlinear; Self-feedback; Neuron; Gau