一种混沌Hopfield网络及其在优化计算中的应用  

A Chaos Hopfield Network and its Application in Optimization Computation

作　　者：徐耀群[1] 孙尧[1] 郝燕玲[1] 

机构地区：[1]哈尔滨工程大学自动化学院

出　　处：《计算机工程与应用》2002年第6期41-42,47,共3页Computer Engineering and Applications

基　　金：黑龙江省自然科学基金项目资助(编号:A00-02);黑龙江省教育厅骨干教师项目资助

摘　　要：文章讨论了神经网络算法在约束优化问题中的应用,提出了一种混沌神经网络模型。在Hopfield网络中引入混沌机制,首先在混沌动态下搜索,然后利用HNN梯度优化搜索。对非线性函数的优化问题仿真表明算法具有很强的克服陷入局部极小能力。This paper is concerned with the application of Hopfield network in the optimization computation.A kind of chaotic neural network is presented,which combines stochastic with deterministic property to introduce chaos mechanism into Hopfield neural network to coarsely search the optimum under chaotic dynamics and control the chaotic dynamics by annealing strategy to perform inverse bifurcation and disappear.After that,the gradient property of HNN is used to reach stable point.Simulation results show that such an algorithm,which is robust with initial states,can avoid getting stuck in local minima and has better convergence property as well as time property.

关 键 词：神经网络 优化算法 混沌 HOPFIELD网络 优化计算 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]