神经网络

Results show that the energy function is Lyapunov stable and the network can be used for finding the minimum covering sphere of a polytope.

第七章 利用有理函数逼近的许多优良特性，构造了一种新的有理连分式链神经网络，给出了网络的一般拓扑结构图和学习算法。

Aiming at the difficulties of invalid solution and local minimum problems when traveling salesman problemis studied using Hopfield artificial neural network.

针对Hopfield神经网络在求解旅行商问题时出现的无效解和局部极小值问题，分析和比较两种改进的求解方法，首先从理论上证明算法的有效性，然后对两种算法分别进行计算机仿真，探讨网络收敛于全局有效解的途径。

The application of ANN for the routing problems in multistage interconnected switch networks has been studied.

研究了神经网络用于多级级联交换网络的路由选择问题。

From the result of training, we can be sure that nerve net model is in good function and can be used to predict the optimum indoor air parameter combination.

从评估结果可以看出该网络模型具有良好的性能，表明利用神经网络预测最佳室内空气参数组合是可行的。

There are two ways to achieve, which will be compared in this paper to have a conclusion: basic nerve net theory of number recognition; and optimized basic theory with modify factor.

本文用了两种方法，第一种为基础的神经网络字符识别算法，第二种为基础方法加入动量因子后对网络进行了优化。

Secondly, author pays more attention to research of optimum indoor air parameter self searching by nerve net simulation, and author used simplified model's data to replace the operating data obtained from measurement in real situation to train the nerve net model.

其次，本文重点研究了最佳室内空气参数组合的自动找寻，编制了相应的Matlab程序，建立了预测最佳室内空气参数组合的神经网络模型，并利用简化模型的计算数据代替实测数据对该网络进行训练。

The Back-Propagation network is one of the most useful Artificial Neural Network, which can deal with complicated data and nonlinear problem.

BP网络是最具有代表性的人工神经网络之一，具有强大的数据处理能力和非线性映射能力。

According to the method,a input/output off-line model and time delay parameter of a unknown time delay process is identified by ULN.The ULN that can be a neural network predictor is used for a prediction model of the time delay systems.

该方法利用本文提出的通用学习网络自适应算法对模型未知的时滞系统进行离线建模，得到该过程的输入输出模型以及系统的滞后时间，进而将辨识得到的神经网络模型作为模型预测器对时滞系统进行预报。

So the input optimization model was solved based on neural network and genetic algorithms, and the optimal process parameters were calculated.

在神经网络模型的基础上结合遗传算法求解网络输入参数优化模型，计算出最佳的工艺参数。

Neural networks ; multiple objective programming/fuzzy optimum selection ; topologic structure of network ; stimulation function ; adjustment of weights

神经网络；多目标规划／模糊优选；网络拓扑结构；激励函数；权重调整

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。