摘要
将切比雪夫多项式引入混沌神经网络的自反馈中,构造一种新的暂态混沌神经网络模型.分析了单神经元的最大Lyapunov指数时间演化图和倒分叉图,以及自反馈项对网络动态特性的影响.通过非线性函数优化和旅行商问题验证了模型有效性.仿真结果显示,新构建的混沌网络模型能有效的避免寻优过程陷入局部极小值的问题.
A new model of transient chaotic neural network was constructed by introducing Chebyshev polynomial into the self-feedback of chaotic neural network.The maximum Lyapunov exponential time evolution and inverted fork graph of single neurons were analyzed,and the effect of self-feedback items on the dynamic characteristics of the network was analyzed.The validity of the model is verified by nonlinear function optimization and traveler problem.The simulation results showed that the newly constructed chaotic network model can effectively avoid the problem of local minimum values in the search process.
作者
徐耀群
杨振华
XU Yao-qun;YANG Zhen-hua(School of Computer and Information Engineering,Harbin University of Commerce,Harbin 150028,China;Institute of System Engineering,Harbin University of Commerce,Harbin 150028,China)
出处
《哈尔滨商业大学学报（自然科学版）》
CAS
2022年第4期414-419,共6页
Journal of Harbin University of Commerce：Natural Sciences Edition
基金
黑龙江省自然科学基金(LH2021F035)“基于自反馈延迟的混沌神经网络及其应用”
黑龙江省教育科学“十三五”规划2020年度重点课题(GJB1320146)“新工科背景下商科高校计算机专业建设与实践”。
