共查询到20条相似文献,搜索用时 15 毫秒
1.
离散Hopfield双向联想记忆神经网络的稳定性分析 总被引:12,自引:0,他引:12
首先将离散Hopfield双向联想记忆神经网络转化成一个特殊的离散Hopfield网络模型.在此基础上,对离散Hopfield双向联想记忆神经网络的全局渐近稳定性和全局指数稳定性进行了新的分析.证明了神经网络连接权矩阵在给定的约束条件下有唯一的而且是渐近稳定的平衡点.利用Lyapunov方程正对角解的存在性得到了几个判定平衡点为全局渐近稳定和全局指数稳定的充分条件.这些条件可以用于设计全局渐近稳定和全局指数稳定的神经网络.所做的分析扩展了以前的稳定性结果. 相似文献
2.
3.
Choon Ki Ahn 《Neural computing & applications》2012,21(5):853-861
In this paper, an error passivation approach is used to derive a new passive and exponential filter for switched Hopfield neural networks with time-delay and noise disturbance. Based on Lyapunov-Krasovskii stability theory, Jensen’s inequality, and linear matrix inequality (LMI), a new sufficient criterion is established such that the filtering error system is exponentially stable and passive from the noise disturbance to the output error. It is shown that the unknown gain matrix of the proposed switched passive filter can be determined by solving a set of LMIs, which can be easily facilitated by using some standard numerical packages. An illustrative example is given to demonstrate the effectiveness of the proposed switched passive filter. 相似文献
4.
针对一类不确定中立型时变时滞Hopfield神经网络的鲁棒稳定性问题, 构造了一个新Lyapunov-Krasovskii泛函, 并结合自由矩阵方法和牛顿—莱布尼茨公式, 得到了新的时滞相关稳定性判据. 该判据考虑了中立型时变时滞Hopfield神经网络中的参数不确定性, 所得结果以线性矩阵不等式(Linear matrix inequality, LMI)的形式给出, 容易验证. 最后, 通过两个数值算例验证了该结果的有效性及可行性. 该判据对丰富与完善中立型神经网络的稳定性理论体系, 具有积极的意义. 相似文献
5.
Hopfield神经网络是一类应用非常成功的人工神经网络模型,它是研究这个反馈神经网络的基础.该文主要研究离散时间、连续状态的反馈神经网络,它是Hopfield神经网络的推广.众所周知,研究反馈神经网络的稳定性不仅被认为是神经网络最基本、最主要的问题之一,同时也是神经网络各种应用的基础.文中主要研究离散时间反馈神经网络的稳定性,给出了连接权矩阵非对称的并且输入-输出函数是一般的S-函数的新的渐近收敛性条件及相应的收敛性结论.所获结果不仅推广了一些已有的结论,而且为反馈神经网络的应用提供了一定的理论基础. 相似文献
6.
7.
二阶神经网络的全局指数稳定性分析 总被引:3,自引:1,他引:2
当神经网络应用于最优化计算时,理想的情形是只有一个全局渐近稳定的平衡点,并且以指数速度趋近于平衡点,从而减少神经网络所需计算时间,二阶神经网络较一般神经网络具有更快的收敛速度,对于二阶连续型Hopfield神经网络,用Lyapunov方法讨论平衡点的全局指数稳定性,给出了平衡点全局指数稳定的几个判别准则,作为特例,获得了连续型Hopfield神经网络全局指数稳定的新判据。 相似文献
8.
This paper investigates the problem of stability analysis for Markovian jumping Hopfield neural networks (MJHNNs) with constant and distributed delays. Some new delay-dependent stochastic stability criteria are derived based on a novel Lyapunov–Krasovskii functional (LKF) approach. These new criteria based on the delay partitioning idea prove to be less conservative, since the conservatism could be notably reduced by thinning the delay partitioning. Numerical examples are provided to show the effectiveness and advantage of the proposed techniques. 相似文献
9.
10.
Xu-Yang Lou Bao-Tong Cui 《国际自动化与计算杂志》2007,4(3):304-314
This paper deals with the problem of delay-dependent robust stability for a class of switched Hopfield neural networks with time-varying structured uncertainties and time-varying delay.Some Lyapunov-Krasovskii functionals are constructed and the linear matrix inequality(LMI)approach and free weighting matrix method are employed to devise some delay-dependent stability criteria which guarantee the existence,uniqueness and global exponential stability of the equilibrium point for all admissible parametric uncertainties.By using Leihniz-Newton formula,free weighting matrices are employed to express this relationship,which implies that the new criteria are less conservative than existing ones.Some examples suggest that the proposed criteria are effective and are an improvement over previous ones. 相似文献
11.
12.
This paper deals with the global asymptotic stability problem for Hopfield neural networks with time-varying delays. By resorting to the integral inequality and constructing a Lyapunov-Krasovskii functional, a novel delay-dependent condition is established to guarantee the existence and global asymptotic stability of the unique equilibrium point for a given delayed Hopfield neural network. This criterion is expressed in terms of linear matrix inequalities (LMIs), which can be easily checked by utilizing the recently developed algorithms for solving LMIs. Examples are provided to demonstrate the effectiveness and reduced conservatism of the proposed condition. 相似文献
13.
The robust stability of a class of Hopfield neural networks with multiple delays and parameter perturbations is analyzed. The sufficient conditions for the global robust stability of equilibrium point are given by way of constructing a suitable Lyapunov functional. The conditions take the form of linear matrix inequality (LMI), so they are computable and verifiable efficiently. Furthermore, all the results are obtained without assuming the differentiability and monotonicity of activation functions. From the viewpoint of system analysis, our results provide sufficient conditions for the global robust stability in a manner that they specify the size of perturbation that Hopfield neural networks can endure when the structure of the network is given. On the other hand, from the viewpoint of system synthesis, our results can answer how to choose the parameters of neural networks to endure a given perturbation. 相似文献
14.
讨论了一类广义时变时滞递归神经网络的平衡点的存在性、唯一性和全局指数稳定性。这个神经网络模型包括时滞Hopfield神经网络,时滞Cellular神经网络,时滞Cohen-Grossberg神经网络作为特例。基于微分不等式技术,利用Brouwer不动点定理并构造合适的Lyapunov函数,得到了保证递归神经网络的平衡点存在、唯一、全局指数稳定的新的充分条件。新的充分条件不要求激励函数的可微性、有界性和单调性,同时减少了对限制条件的要求。两个仿真例子表明了所得结果的有效性。 相似文献
15.
16.
17.
Bruce D. Calvert 《Systems & Control Letters》2000,40(1):31
We study an ordinary differential equation which models the behaviour of a class of neural networks, which are similar to the Hopfield networks, and which can give convergence in finite time. For application to optimisation problems, and other applications, we are concerned with global asymptotic stability. This paper gives new results on this topic. 相似文献
18.
基于暂态混沌神经网络的组播路由算法 总被引:4,自引:0,他引:4
讨论了高速包交换计算机网络中具有端到端时延的组播路由问题。首先给出了这类问题的网络模型及其数学描述,然后提出了基于暂态混沌神经网络的组播路由算法。实验结果表明,该算法能够快速有效地实现组播路由优化,并且计算性能及解的质量优于基于Hopfield神经网络的路由算法。 相似文献
19.
通过构造适当的Lyapunov函数,利用Halanay不等式和Young不等式,讨论一类具有变时滞的Hopfield型神经网络的全局指数稳定性.在对网络施加两个不同的神经元激励函数的条件下,导出网络全局指数稳定的一个充分条件,得到的充分条件在实际应用中易于验证,且有较小的保守性,因而对网络的应用和设计具有重要意义.最后,一个数值实例进一步验证结果的正确性. 相似文献