神经网络

With the unique advantage of the Nerval Network dealing with the complex non-lineal problem and the data documents of the ground subsidence in the power plant, the BP network model is set up and then is confirmed to be effective and accurate in predicting the movement through training and testing.

利用神经网络处理复杂的非线性问题的独特优势，根据发电厂地表移动的观测数据资料建立了BP网络模型，经过训练和测试证明了该网络在发电厂地表移动预测中的有效性和精确性。

The network structure is significant in characterizing the performance of the feedforward network, such as network capacity, learning speed, generalization ability Standard back propagation performs gradient descent only in the weight space of a network with fixed topology, in general, it is useful only when the network architecture is chosen correctly With a bad structure we potentially run into problems like underfitting, overfitting or wasting computational resources, so algorithms than can find an appropriate network architecture automatically are highly attractive.

神经网络的结构对于前向网络的特性有重要的影响，如网络容量，学习速度，泛化能力等。标准BP算法是针对网络结构是固定的情况下搜索权值，一般来说，这只能在网络结构被正确选取才有用。如果网络结构不当，我们可能会欠拟合、过拟合或浪费计算资源，因此如果能找到能自动选取网络结构的算法是很有吸引力的。

On account of the fact that power system is an intense non-linear, time-varying system which consists of a great many of dynamic unmodeled characteristics and tends to become more complicated, this paper adopts ANN to complete the forecasting task of short term and ultra short term load.

本文采用人工神经网络系统的智能化预测方法进行配电网的短期和超短期负荷预测，对Kohonen网络和BP网络在负荷预测中的应用进行了分析，并给出了综合负荷预测方法的仿真算例。

The work has been emulated and analyzed by computers, and a computer network fault diagnosis system has been excogitated.

在BP神经网络算法上对LM算法进行改进，对在LM算法中的大型矩阵求逆时使用并行算法求解线性方程组的方式加以改进，并使用计算机网络故障诊断作为实际算例进行计算机仿真和分析，开发了一套计算机网络诊断系统，以期能对理论研究和应用工作提供参考和帮助。

In chapter 6 the training and testing process of Bp network and SOFM network using 100 fabric samples, and the assessed results of pilling grade by neural network are presented.

第六章介绍了用100个起球织物试样对Bp网络和自组织神经网络进行训练和测试的过程以及网络的评定结果。

Radial Basis Function Neural Network is adapted to improve the structure of Dynamic Matrix Control algorithm in this paper.

利用RBF网络对DMC算法进行结构上的改进，并用RBF网络的逼近性能建立预测模型，提出一种基于RBF神经网络建模的动态矩阵控制算法，并用该算法对典型的时滞系统进行仿真试验，结果表明该算法具有较高的控制精度和响应速度

The study on the pre-estimation of rice noodle quality by ANN showed that the trained BP network model calculated the quality effectively with the mechanics properties and rice characters. In the model, the number of neural cells (the number of the input vectors+2) in the hidden layer was satisfied with the requirement of the network.

通过采用人工神经网络对米粉品质预测的研究，认为可采用经过训练的BP网络对米粉力学性质及原料米特性对米粉品质进行有效的预测；在此类网络模型的设计中，采用一个含有（实际输入分量数+2）个神经元数的隐含层即可满足设计要求。

At the same time, I also discussed the theory of fancy yarn"s forming in Hollow Spindle and Ring Spindle Twisting Machine, twisting degree of fancy yarn"s and fancy yarn"s winding in detail in the dissertation. What"s more, I analyzed the model and the learning arithmetic of representative feedback Neural-Network--BP Neural-Network. All these make the control system that I empoldered have strong theoretic foundation.

本论文还对'空心锭一环锭花式捻线机的成纱原理、花式纱线的捻度以及花式纱线的卷绕等进行了详细地分析和说明；也对本课题采用的神经网络模型一一典型前向网络一一BP网络模型的学习算法进行了详尽的分析和说明，这些使得本课题所开发的控制系统有了较强的理论基础。

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。。。

Hopfield networks have learning capabilities; the circuit in this design idea can apply different adaptive-learning rules by using alternative comparator-inverter/comparator-follower schemes, conductance-node-layout schemes—reciprocals of the feedback resistances—between the input comparators, and bit-order readouts.

参考和模拟输入电压驱动神经网络，数字输出来源于网络中的比较器。hopfield网络具有学习能力；本设计方案的电路采用不同的自适应学习规则，通过使用可选的比较器-转换器/比较器-跟随器方案，电导节点规划方案——反馈电阻的倒数——在输入比较器之间，和位顺序读出器。

We have no common name for a mime of Sophron or Xenarchus and a Socratic Conversation; and we should still be without one even if the imitation in the two instances were in trimeters or elegiacs or some other kind of verse--though it is the way with people to tack on 'poet' to the name of a metre, and talk of elegiac-poets and epic-poets, thinking that they call them poets not by reason of the imitative nature of their work, but indiscriminately by reason of the metre they write in.

索夫农 、森那库斯和苏格拉底式的对话采用的模仿没有一个公共的名称；三音步诗、挽歌体或其他类型的诗的模仿也没有——人们把&诗人&这一名词和格律名称结合到一起，称之为挽歌体诗人或者史诗诗人，他们被称为诗人，似乎只是因为遵守格律写作，而非他们作品的模仿本质。

The relationship between communicative competence and grammar teaching should be that of the ends and the means.

交际能力和语法的关系应该是目标与途径的关系。