查询词典 neural network

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。

It employs the complex-valued step function to build neural model, then constructs network structure and decides the number of neurons; it adopts complex-valued Hebbian rules and inner product way to calculate the net weight matrix; then it analyzes the convergence of the network by taking advantage of the definition of energy function. In the image pre-processing stage, 2-dimensional Fourier Transform and Euler's formula are used, respectively, to transfer a gray-scaled image into phase information needed by the complex-valued neural network when stores the traffic sign. In the image post-processing stage, phase inverse transformation is used to change the phase image to gray-scaled image.

采用复数阶跃函数构建了神经元模型，建立了复数Hopfield神经网络结构，并且确定了网络中神经元的个数；借助复数Hebbian学习规则和复数内积法给出了网络权值的确定方法；借用复数网络能量函数的定义，说明了复数识别网络的收敛性；在前期的图像数据处理部分，分别使用离散二维傅里叶变换和欧拉公式，给出了将灰度图像数据转化为复数网络所需要的相位信息的方法，实现了网络对路牌的记忆存储；在后期的图像还原部分利用相位逆变换的方法，实现了相位图到灰度图转化。

The effects of the initial values and the network approximation error using neural network model composed of feedforward neural net and delayed output feedback in the approximation of NARMAX system are studied, and a conclusion is drawn that under some weak conditions the output of the network model has little difference from that of the actual system.

研究了用带有延迟环节的前馈网组成的网络模型逼近NARMAX系统时网络逼近误差及运行初始误差对网络模型输出的影响，指出在一些弱的条件下网络模型输出与实际系统输出间相差不大。

Considering the shortcoming of overlong network training time of BP neural network in multidimensional data classification,a new multiple neural network classification model is presented.

0引言高维数据的分类是一个重要而且具有挑战性的问题，基于BP神经网络的分类方法是一种有效的方法，具有较强的分类能力和鲁棒性。

To sum up, main results of this study were listed as follows:(1) After analyzing the main factors affecting generalization function of neural network, and aiming at poor representativity of hydrologic time series samples, standardization method of transforming extreme was presented to deal with input sample of time series, which could make the input samples lie in the interpolation range of training samples even if they lie in the extension of training samples, so it improved generalization function of neural network and accelerates network convergence speed.

概括起来，本文取得的主要研究成果如下：(1)对影响神经网络泛化能力的主要原因进行了阐述，针对水文时间序列样本的代表性不好这一问题，提出了采用变最值的规范化方法处理时间序列输入样本，使神经网络的输入样本即使为训练样本的外延，规范化后也处于训练样本的内插范围，从而改善神经网络的泛化能力，并加快网络收敛速度。

Self-generating neural network is a self-organization neural network, whose network structures and parameters need not to be set by users, and its learning process needs no iteration.

自生成神经网络是一类自组织神经网络，它不需要用户指定网络结构和学习参数，而且不需要迭代学习，是一类特点突出的神经网络。

In this paper, many sensor networks are distributed at different areas, firstly the local fuzzy neural network fuses the information from corresponding sensor network in character level, secondly the outputs,which are diagnosis conclusion, are fused by terminal neural network in decision level.

电力系统的继电保护和故障诊断一直是人们研究的重要课题，一旦系统发生故障，如何尽快识别故障类型、判断故障位置、及时跳闸保护以及故障排除后迅速恢复供电等，开发出这样一个实用可靠的继电保护和故障诊断系统势在必行。

Aiming at T-base diamond lathe, author use both on-line and off-line to measure the error vector of lathe workspace, and acquire good network train samples, then build two-dimensional error compensation model of lathe workspace with BP neural network and fuzzy neural network, at last build contour error compensation control system.

在分析国内外数控机床伺服闭环系统的发展现状及局限性的基础上，利用原数控系统和所研制的二维压电陶瓷微动刀架，研制了独立于原数控系统的超精密闭环控制系统。

By combining model reference adaptive control and neural network control ,a novel model reference adaptive neural network control scheme is proposed for the ship steerings nonlinear model.In the procedure ,the RBF neural networks are used to approximate nonlinear systems;The weights can be achieved by use of Lyapunove approach.To compensate the approximation error and attenuate the external disturbance,a robust technology is introduced to the proposed scheme.

针对船舶航向非线性不确定系统，提出了一种把神经网络和模型参考自适应控制结合在一起的新的控制算法，此算法首先通过系统的已知动态特性设计一个稳定的反馈控制器，然后利用RBF神经网络逼近未知非线性，从而消除不确定性的影响。

The main contents of the thesis include: the requirements analysis of neural computation to neurochip; the architecture of digital general-purpose neurochip; the design and implementation of neurochip hardware; the architectures of neurocomputer that can be built out of the neurochip; the neural network mapping algorithms; the user integrated developing environment with friendly interface; and the study of algorithms for neural network models.

本文的主要研究内容有：神经计算对神经芯片的需求分析；通用数字神经芯片体系结构；芯片硬件的设计与实现；基于神经芯片的神经机系统结构；神经网络映射算法；友好的用户开发环境；神经网络算法，等等。

Neither the killing of Mr Zarqawi nor any breakthrough on the political front will stop the insurgency and the fratricidal murders in their tracks.

在对危险的南部地区访问时，他斥责什叶派民兵领导人对中央集权的挑衅行为。

In fact,I've got him on the satellite mobile right now.

实际上 我们已接通卫星可视电话了