神经网络

A fixed point of a discrete-time neural network with generalized input-output function and by using the converse theorem of Lyapunov function we study the uniformly asymptotical stability of equilibrium in this discrete-time neural network with variable weight and give some sufficient conditions that guarantee the stability of it.

本文首先介绍了几类离散神经网络模型的由来及其研究概况，利用Schauder不动点原理证明了一类具有广义输入输出函数的离散神经网络模型平衡点的存在性，利用Lyapunov函数逆定理给出了这类离散神经网络模型在时变权值下的一致渐近稳定性的充分条件。

In this thesis, we firstly introduce several class of discrete-time neural network models and the research progress of the neural networks. By Schauder fixed-point principle we prove the existence of an equilibrium (i.e. a fixed point) of a discrete-time neural network with generalized input-output function and by using the converse theorem of Lyapunov function we study the uniformly asymptotical stability of equilibrium in this discrete-time neural network with variable weight and give some sufficient conditions that guarantee the stability of it.

本文首先介绍了几类离散神经网络模型的由来及其研究概况，利用Schauder不动点原理证明了一类具有广义输入输出函数的离散神经网络模型平衡点的存在性，利用Lyapunov函数逆定理给出了这类离散神经网络模型在时变权值下的一致渐近稳定性的充分条件。

For the limitations of the traditional algorithms that can not be reasonably used to predict the traffic, this paper adopted the BP neural network and curvilinear regression coupling algorithms to add the inadequate.

摘 要：针对传统交通量预测方法中的局限性，采用BP神经网络与曲线回归耦合算法，用BP神经网络对历史数据训练，利用曲线回归对各因素待测年份之值进行预测，将各因素的预测值带入已训练好的BP神经网络中，即可得到未来交通量的预测值。

For the limitations of traditional algorithms that can not be reasonably accurately predict the traffic, we have adopted BP neural network and curvilinear regression algorithms. First, we use BP neural network to train on historical data and then use the curve of regression to predict various factors, and then forecast data into the trained BP neural network which has been trained well, you can get future traffic forecasts.

针对以上传统算法的局限性，采用BP神经网络与曲线回归耦合算法，用BP神经网络对历史数据训练，利用曲线回归对各因素待测年份之值预测，将各因素的预测值带入已训练好的BP神经网络中，即可得到未来交通量的预测值。

The mathematical model of the dynamic recurrent neural networks with two hidden layers is introduced. Using the experimental data, the neural identifier and the neural controller are designed off-line.

介绍了双隐层动态递归神经网络的数学模型，利用实验数据离线设计了神经网络辨识器与神经网络控制器。

By transforming the delayed neural model to the describer model and then employing the Lyapunov-Krasovskii stability theorem, linear matrix inequality LMI technique, S procedure, and some algebraic inequality method, a new sufficient condition is derived, which is determined by the coefficients of the model and includes more tuning parameters for determining the globally asymptotical stability of recurrent neural networks with time-varying delay.

首先将要研究的模型转化为描述系统模型，然后利用Lyapunov-Krasovskii稳定性定理、线性矩阵不等式技术、S过程和代数不等式方法，得到了确保时变时滞递归神经网络渐近稳定性的新的充分条件，并将它应用于常时滞神经网络和时滞细胞神经网络模型，分别得到了相应的全局渐近稳定性条件。

The neural network has the good project application prospect, and it is considered as the most potential diagnostic tool.

本文首先对神经网络和当前飞机发动机故障诊断技术进行了介绍，结合神经网络的一些特性，对神经网络用于故障诊断的优点进行了分析。

So it is difficult to distinguish them using traditional neural network classification. A face distinguishment approach based on multi-stage neural networks is proposed.

为此，本文提出一种基于多级分类神经网络级联的人脸判别方法，通过把基于不同颜色分量的多级神经网络级联起来，并利用不同颜色分量由于来源、定义、算法的不同而体现出来的不同特性，以不同的颜色分量图象作为各级神经网络的分类特征，有效提高了人脸判别的正确率。

The emulations and experimental results indicate that the theoretical model combined the neural network and genetic algorithm not only can conquer the disadvantage, which network is prone to enmesh the partial minimal error, but also utilize the powerful artificial intelligence of neural network.; This model provides a new method and idea for the monitor systems management, meanwhile it also offer a new method for solving the problems of the undetermined information processing; This model has powerful studying function, high accuracy, and strong practicability, so it has promoted value.

仿真及实验结果表明：由于此数学模型是将神经网络和遗传算法相结合应用在井下的监控系统中，因此即克服了神经网络容易陷入局部最小误差的缺点，又利用了神经网络本身强大的人工智能；该模型不仅为煤矿监控系统管理提供了一种新方法和新思路，同时也为解决不确定性信息处理问题提供了一种新的尝试和手段；该模型学习功能强大，精度较高，实用性强，具有很好的推广价值。

The results indicate that the ANN structure and the training sample have some impact on the prediction precision. The real time measured power as input will improve the precision of 30 min ahead prediction, however will decrease the precision of 1h ahead prediction. The results which using the atmospheric data at all different heights as input have a higher accuracy when compared with the results using hub height data only. The designed ANN can forecast the error band.

研究结果表明，神经网络的结构和输入样本对预测结果有一定的影响；实测功率数据作为输入可以提高提前量为30 min的预测精度，而对提前量为1 h的预测精度会降低；把不同高度的数据都作为神经网络的输入比只采用轮毂高度数据的预测精度高；设计的神经网络能够对误差带进行预测。

Singer Leona Lewis and former Led Zeppelin guitarist Jimmy Page emerged as the bus transformed into a grass-covered carnival float, and the pair combined for a rendition of "Whole Lotta Love".

歌手leona刘易斯和前率领的飞艇的吉他手吉米页出现巴士转化为基层所涵盖的嘉年华花车，和一双合并为一移交&整个lotta爱&。

This is Kate, and that's Erin.

这是凯特，那个是爱朗。