数学神经网络(V)──某些数学方法的神经网络表示

继续研究数学神经网络，这里提出一种观点：人工神经网络可以作为数学的一种可视化手段．首先用例子指出几种熟知的数学方法可以用神经网络表达，然后讨论了线性规划、多目标线性规划、模糊线性规划以及模糊关系方程的神经网络形式．     

神经网络反传模型的理论与应用研究体会

神经网络及神经计算的新理论，模型，方法及应用受重视，并用于解决某些诸如模式识别，组合优化，语言理解等复杂问题，得到系列可喜的理论成查与实际应用。我们业已将神经网络反传模型应用于多元校正，有机合成，模式识别，构效关系及分子设计等方面。     

Sigma—pi神经网络激发函数特征

研究了ｓｉｇｍａ－ｐｉ这一类神经网络激发函数的特征，给出能作为这类激发函数的充要条件，并具体给出了其表达式。     

基于滑动概率神经网络的早期故障诊断

针对机电设备早期故障难以识别的问题，提出了一种动态的概率密度估计方法——滑动概率神经网络，用以跟踪分析测量信号的概率密度变化过程，及时发现早期故障．该网络以固定不变的抽样集作为第一层，动态滑动的测量信号作为样本层，通过求和层得到抽样集的条件概率密度估计，将样本层内测量信号的概率密度动态地投影到统一的抽样集上．将网络分解成以测量值为中心的子网络，来实现网络的递归运算，并且利用高斯函数的快速衰减特性或使用分段线性函数近似高斯函数，从而提高了网络的计算实时性．通过压缩机喘振过程数据的应用实例，表明该方法能够有效识剐故障的早期征兆．     

无线传感器网络研究

介绍了无线传感器网络的体系结构、特点,分析了无线传感器网络研究的一些关键性问题,探讨了无线传感器网络的应用范围。     

Adaptive control of system with hysteresis using neural networks

1.INTRODUCTIONThe piezoelectric actuators are well suited for micro-position devices in precision engineering because oftheir fast response,nanometer resolution and biggerdriving force[1].However,hysteresis inherent topiezoelectric actuator severely li mits system’s perfor-mance such as giving rise to undesirable accuracy oroscillations,even leading to instability.Hysteresischaracteristics are generally nondifferentiable andusually unknown.It is a difficult task to mitigate itsharmful ef…     

Multicast routing algorithm of multiple QoS based on widest-bandwidth

1 .INTRODUCTIONA mobile Ad hoc network refers to a temporal multi-hop autonomy system,whichis constituted by a groupof mobile nodes containing wireless send-receive equip-ments[1].It possesses manycharacteristics-fast-deploy-able,self-organized,acentric , movable and of multi-hop.It can be wildly applied to many fields ,such asnational defense,emergency and disaster ,scientificin-vestigation and exploration etc .,and uponthat ,it hasgreat prospects[1 ,3 6]. With the wide spread of mo-bile…     

Research on Chaotic Time Series Prediction Based on K-entropy and RBF Neural Networks

In this paper, a method of direct multi-step prediction of chaotic time series is proposed, which is based on Kolmogorov entropy and radial basis functions neural networks. This is done first by reconstructing a phase space using chaotic time series, then using K-entropy as a quantitative parameter to obtain the maximum predictability time of chaotic time series, finally the predicted chaotic time series data can be acquired by using RBFNN. The application considered is Lorenz system. Simulation results for direct multi-step prediction method are compared with recurrence multi-step prediction method. The results indicate that the direct multi-step prediction is more accurate and rapid than the recurrence multi-step prediction within the maximum predictability time of chaotic time series. So, it is convenient to forecast and control with real time using the method of direct multi-step prediction.     

一种修正的SPAWG算法

最小费用半光路问题是指在给定的全光WDM网络条件下，在源节点和目的节点之间找一条费用最小的半光路由．与一般的最小路问题不同的是网络在节点上还有与链路相关的费用函数，对Chlamtac等人的SPAWG算法，给出了一种修正的SPAWG算法。     

离散Hopfield神经网络的动态行为分析

离散Hopfield神经网络的稳定性不仅本身有重要的理论意义，而且也是网络应用的基础。主要研究非对称离散Hopfield神经网络在并行演化模式下的动力学行为，得到了一些新的稳定性条件，所获结果进一步推广了一些已有的结论。