查询词典 neural network

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。

And we used them into the inspection of these polluted gases. We used them because the constringent speed of wavelet neural network is very fast, they are not sensitive to the inputs of the network and they have the characteristic that they also can effectively approach the functions or signals. Classical neural networks mostly train the network with back propagation algorithm.

在目前常用的一维小波神经网络的基础上，我们研究了用来处理多维数据信息的小波神经网络，并将其应用于室内混合气体检测，主要是基于小波神经网络学习收敛速度较快，对网络输入不是很敏感，以及小波神经网络可以有效的进行函数逼近或者信号逼近的特点。

According to the actual circumstance of performance evaluation for mechanical products, the general neural network is reformed. Therefore, we construct the fuzzy neural network. This paper expresses membership function in the network by trapezium formulae .The indicators are fuzzed using the membership function .

网络中采用梯形函数的四元组形式构造模糊隶属函数，并用隶属函数的端点值和中间值作为样本，用改进的反向传播算法训练网络，得到与待评价产品情况相符合的权重值。

Reliability evaluation of existing structures is shown from the angle of artificial neural network. The influencing factors and deformation characteristics of buildings above goafs are summarized based on the code of coal pillar design and pressed coal mining for buildings, water-bodies, railroads and main mine roadway. The model of neural network is build to solve the problems about complex influencing factors and long evaluating time of building evaluation. BP network model compared with traditional way has strong practicability and extension value.

本文从人工神经网络的角度着手，基于国家煤炭工业《建筑物、水体、铁路及主要井巷煤柱留设与压煤开采规程》，分析了采动区建筑结构的影响因素和变形特性，运用已有的采动区建筑物可靠性评估实例，建立了BP人工神经网络可靠性评估模型，对采动区在役结构可靠性进行了评估，较好地解决了采动区建筑物可靠性评估影响因素复杂和耗时长的问题。

Then the self-recurrent neural network structure, one kind of simplified structure of internal recurrent network, and the leaming algorithm, dynamic backpropogation algorithm of self-recurrent neural network, is proposed.

本文将神经网络作为传统的线性模型的非线性推广进行了分析，证实了多层前向神经网络与非线性自回归模型的等价意义，及带有反馈的循环神经网络与非线性自回归移动平均模型的等价意义。

The deviation compensation algorithm put forward here is analyzed in theory and the effect of this compensation algorithm is testified based on experimental results that the learning speed of this network can be sped up markedly and all attitude magnetic heading error can be greatly reduced. RBF neural network is quite effective and superior to BP neural network.

在分析算法原理的基础上进行了实验仿真，结果表明：采用RBF神经网络在明显提高网络收敛速度的基础上，大大减小了全姿态磁航向误差，校正效果优于BP神经网络。

Nowadays, distributed intrusion detection system research based on the technology of agent and neural network becomes hotspot, software agent technology is considered as a very tool to develop intrusion detection system, especially its characteristic of Autonomy, Social Ability and Adaptability, and neural network technology gains more and more focus in respect that its pre-estimation to unknown network activities.

目前，基于Agent和神经网络技术的分布式入侵检测系统的研究成为业界热点，软件Agent技术因其所具有的良好的自治性、社会性、适应性，被视为在入侵检测系统中极为有用的技术之一，而神经网络技术则因其对未知网络行为的预判性，在入侵检测系统领域得到越来越多的关注。

The three-layered feedforward neural network and its learning methods are studied in this work, where new neural network model and the network learning algorithms are presented.

本文主要研究三层前向神经网络及其学习问题，在此基础上提出新的网络模型和学习算法，目的是为了克服基于传统的BP算法的前向网络存在的网络结构和。。。

BP neural networks have been widely used in mode recognizing, image processing, system control etc A lot of study has been done on the training algorithm of BP neural networks But there are still many short comings To complete the training of the weights of a BP neural network, the key problem is how to overcome the staying at the local minimum points as well as how to increase the training speed based on this condition This paper comes up w...

BP神经网络被广泛应用于分类模式识别、图像处理和系统控制等领域人们对BP网络算法进行了许多的研究，但尚有其不足之处为完成其权的训练，问题的关键在于如何避免陷入局部极小及在此前题下如何提高学习速度为此，就如何选取学习率η和动量矩α提出了改进方案，并应用于数字识别，得到了较为满意的结果

Looking to bounce back from defeat against Cesena last weekend, the Calabrian boss will be sticking to his tried and tested 4-3-3, with Lopez and Sedivic joined up front in Giampaolo's absence by either Nanni or Plasmati.

鉴于上周末对切塞纳的比赛中反败为胜，这支南方球队将会更坚持其一贯而有效的4-3-3阵型，洛佩斯和塞德维奇将取代受伤缺席的詹保罗，和纳尼或者帕斯马蒂中的一个搭档锋线。

Meanwhile, their exposure to the more freewheeling ways of the West broadened dramatically.

另外，西方较自由的生活方式对年轻人的影响增大。