时滞递归神经网络中神经抑制的作用

研究了具有时滞的二阶递归神经网络中抑制自连接的作用，给出了时滞依赖的全局渐近稳定的充分判据.研究结果表明：抑制自连接可镇定不稳定的网络并使其渐近稳定；抑制自连接的镇定作用受到网络传输时滞的制约.仿真示例验证了结果的有效性. 关键词： 递归神经网络 时滞 抑制神经元 动态行为     

双向联想记忆神经网络及其在肺癌患者分类判别中的应用

给出双向联想记忆（BAM）神经网络的基本原理，在此基础上，根据血清中微量元素的含量，将双向联想记忆神经网络用于正常人与肺癌患者的分类判别。实验结果表明，用独立预测样本作检验，在本工作所选定的条件下，可以达到100％的正确识别率，并讨论了双向联想记忆神经网络的影响因素。     

变频正弦混沌神经网络及其应用

针对暂态混沌神经网络全局寻优能力受限的问题,提出了一种基于脑电波生物机制的新型混沌神经网络模型——变频正弦混沌神经网络.该模型将变频正弦函数和Sigmoid函数组合作为非单调激励函数,本文给出了该混沌神经元的倒分岔图及Lyapunov指数的时间演化图,分析了其动力学特性.进一步将该模型应用到非线性函数优化和组合优化问题上,并分析了参数的变化规律.仿真实验证明变频正弦混沌神经网络比暂态混沌神经网络及其他相关模型具有更好的全局寻优能力.     

时滞离散神经网络的同步控制

利用既有效又便于实施的时滞状态反馈控制器,根据所给定的条件构造相应的不等式,研究了带有时滞的离散神经网络模型的同步控制问题,给出了该离散系统指数同步的充分条件.在设计同步控制的时候,没有假设激励函数的有界性、可微性和单调性,给出的条件简便易实施.数值结果进一步证明了该控制方法的有效性. 关键词： 离散神经网络 时滞 同步     

双极双向联想存储器的单通道光学实现

以附加神经元引入附加背景的方式获得将线性离散比极神经元的神经网络在单通道光学矢量-矩阵乘法器内实现的方法,给出了相应的光学系统的修正和非负光学模板的编码形式.以双极神经元的双向联想存储器为例进行了计算机和光电实验模拟.     

不确定分数阶时滞混沌系统自适应神经网络同步控制

针对带有完全未知的非线性不确定项和外界扰动的异结构分数阶时滞混沌系统的同步问题,基于Lyapunov稳定性理论,设计了自适应径向基函数(radial basis function,RBF)神经网络控制器以及整数阶的参数自适应律.该控制器结合了RBF神经网络和自适应控制技术,RBF神经网络用来逼近未知非线性函数,自适应律用于调整控制器中相应的参数.构造平方Lyapunov函数进行稳定性分析,基于Barbalat引理证明了同步误差渐近趋于零.数值仿真结果表明了该控制器的有效性.     

一类混沌神经网络的全局同步

研究了一类时滞混沌神经网络的全局同步问题.应用驱动-响应同步方法和线性矩阵不等式技术，给出了时滞混沌神经网络全局同步的充分条件和同步控制器设计方法，而且所得到的控制器易于实现.仿真示例验证了本文方法的有效性. 关键词： 混沌神经网络 同步 驱动-响应法 线性矩阵不等式     

不确定时滞混沌系统的自适应动态神经网络控制

研究了一类具有不确定时滞的非自治混沌系统的控制问题. 通过结合Lyapunov-Krasovskii函数和Lyapunov函数设计参数可调的不确定时滞补偿器,使得反馈控制输入信号不受时延的影响;同时引入动态结构自适应神经网络,以消除系统的不确定性,其隐层神经元的个数可以随着逼近误差的增大而自适应增加,改善了逼近速度与网络复杂度的关系;最后,用Duffing混沌系统的控制仿真示例表明该方法的有效性. 关键词： 混沌系统 自适应控制 不确定时滞 动态结构神经网络     

神经系统中随机和混沌感知信号的联想记忆与分割

为了模拟人与动物感知信息的真实环境，以脉动神经元节点组成神经元网络，研究在随机刺激和混沌刺激等极端条件下的记忆模式存储与时间分割问题.研究表明：网络对于若干种模式的叠加输入，能够以一部分神经元同步发放的形式在时间域上分割出每一模式. 如果输入模式是缺损的，系统能够把它们恢复到原型，即具有联想记忆功能.通过调节耦合强度和噪声强度等参数使得网络在中等强度噪声达到最优的时间分割，与广泛讨论的随机共振现象一致. 关键词： 神经网络 空时模式 联想记忆 随机共振     

神经元传输函数对人工神经网络动力学特性的影响

以神经元局域场分布为基础，重新研究了连续神经元传输函数对具有联想记忆的人工神经网络功能的影响.与以往的认识不同的是，研究发现连续传输函数与硬极限传输函数相比并不存在明显的优越性，相反，连续传输函数对网络的某些功能，如最大存储率具有负面影响.研究表明神经网络的特性主要决定于网络的动力学结构(具体体现为网络吸引子对应的神经元局域场分布)，网络的动力学结构可以通过选择合适的设计规则进行有效控制，不同的传输函数虽然也能影响到网络的动力学结构，但是它所带来的影响是被动的，可控性很差. 关键词： 联想记忆 神经网络 吸引子 局域场分布     

Convergence analysis of stochastic hybrid bidirectional associative memory neural networks with delays

The stability property of stochastic hybrid bidirectional associate memory (BAM) neural networks with discrete delays is considered. Without assuming the symmetry of synaptic connection weights and the monotonicity and differentiability of activation functions, the delay-independent sufficient conditions to guarantee the exponential stability of the equilibrium solution for such networks are given by using the nonnegative semimartingale convergence theorem.     

Multistability in bidirectional associative memory neural networks

In this Letter, the multistability issue is studied for Bidirectional Associative Memory (BAM) neural networks. Based on the existence and stability analysis of the neural networks with or without delay, it is found that the 2n-dimensional networks can have n³ equilibria and n² equilibria of them are locally exponentially stable, where each layer of the BAM network has n neurons. Furthermore, the results has been extended to (n+m)-dimensional BAM neural networks, where there are n and m neurons on the two layers respectively. Finally, two numerical examples are presented to illustrate the validity of our results.     

Input-to-state stability analysis for memristive BAM neural networks with variable time delays

In this paper, we are concerned with input-to-state stability of a class of memristive bidirectional associative memory (BAM) neural networks with variable time delays. Based on a nonsmooth analysis and set-valued maps, some novel sufficient conditions are obtained for the input-to-state stability of such networks, which extended some known results as particular cases. Finally, a numerical example is presented to illustrate the feasibility and effectiveness of our results.     

Robust stability for uncertain stochastic fuzzy BAM neural networks with time-varying delays

In this Letter, by utilizing the Lyapunov functional and combining with the linear matrix inequality (LMI) approach, we analyze the global asymptotic stability of uncertain stochastic fuzzy Bidirectional Associative Memory (BAM) neural networks with time-varying delays which are represented by the Takagi-Sugeno (TS) fuzzy models. A new class of uncertain stochastic fuzzy BAM neural networks with time varying delays has been studied and sufficient conditions have been derived to obtain conservative result in stochastic settings. The developed results are more general than those reported in the earlier literatures. In addition, the numerical examples are provided to illustrate the applicability of the result using LMI toolbox in MATLAB.     

Multistability of delayed complex-valued recurrent neural networks with discontinuous real-imaginarytype activation functions

In this paper, the multistability issue is discussed for delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions. Based on a fixed theorem and stability definition, sufficient criteria are established for the existence and stability of multiple equilibria of complex-valued recurrent neural networks. The number of stable equilibria is larger than that of real-valued recurrent neural networks, which can be used to achieve high-capacity associative memories. One numerical example is provided to show the effectiveness and superiority of the presented results.     

Delay-range-dependent stability for fuzzy BAM neural networks with time-varying delays

This Letter considers the problem of delay-range-dependent stability for fuzzy bi-directional associative memory (BAM) neural networks with time-varying interval delays. Based on Lyapunov-Krasovskii theory, the delay-range-dependent stability criteria are derived in terms of linear matrix inequalities (LMIs). By constructing new Lyapunov-Krasovskii functional, stability conditions are dependent on the upper and lower bounds of the delays, which is made possible by using some advanced techniques for achieving delay dependence. A numerical example is given to illustrate the effectiveness of the proposed method.     

Global exponential stability of Cohen–Grossberg neural networks with variable delays

In this Letter, the conditions ensuring existence, uniqueness of the equilibrium point of Cohen–Grossberg neural networks with variable delays are obtained under more general assumption about activation functions. Applying idea of vector Liapunov function, and M-matrix theory, the sufficient conditions for global exponential stability of Cohen–Grossberg neural networks are obtained. These results generalize a few previous known results and remove some restrictions on the neural networks.     

Analysis of global exponential stability for a class of bi—directional associative memory networks

In real-time applications of bi-directional associative memory (BAM) networks.a global exponentially stable equilibrium is highly desired.The existence,uniqueness and global exponential stability for a class of BAM networks are studied in this paper,the signal function of neurons is assumed to be piece-wise linear from the engineering point of view.A very concise condition for the equilbrium of such a network being globally exponentially stable is derived.which makes the pactical design of this kind of networks an easy job.     

Periodic oscillatory solution of bidirectional associative memory networks with delays

Periodic oscillatory phenomena of bidirectional associative memory (BAM) networks with axonal signal transmission delays are investigated by constructing suitable Lyapunov functionals and some analysis techniques. Some simple sufficient conditions are derived ensuring the existence and uniqueness of periodic oscillatory solutions of the BAM with delays, and all other solutions of the BAM converge exponentially to a periodic oscillatory solution. These conditions are presented in terms of system parameters, and have an important leading significance in the design and applications of periodic oscillatory neural circuits for the BAM with delays.     

Novel global robust stability criteria for interval neural networks with multiple time-varying delays

This Letter is concerned with the problem of robust stability analysis for interval neural networks with multiple time-varying delays and parameter uncertainties. The parameter uncertainties are assumed to be bounded in given compact sets and the activation functions are supposed to be bounded and globally Lipschitz continuous. A sufficient condition is obtained by means of Lyapunov functionals, which guarantees the existence, uniqueness and global asymptotic stability of the delayed neural network for all admissible uncertainties. This condition is in terms of a linear matrix inequality (LMI), which can be easily checked by using recently developed algorithms in solving LMIs. Finally, a numerical example is provided to demonstrate the effectiveness of the proposed method.