神经网络

An Ellipsoidal Basis Function can make the partition of input space and make a limitary and bounded.

椭球基函数（Ellipsoidal Basis Function，EBF）使网络划分输入空间成为封闭有界的局部作用的空间，与径向基函数（Radial Basis Function，RBF）神经网络的高斯函数相比，它对空间的划分更明确。

The SMLMS Algorithm for the Multilayer Feedforward neural Network This part analyzes the misadjustment noise introduced by the momentum factor α for traditional error Back-Propagation algorithm, and demonstrates that it is a nonnegligible factor to effect the convergent precision of the neural network.

第三章通过分析传统BP算法中存在的动量误调噪声对整个网络的收敛精度所造成的影响，确认传统BP算法中的动量误调噪声对多层前向神经网络的学习确有不可忽略的消极作用。

Through training and simulating the data came from the indoor simulation orthogonally experiment and the field survey, the web model based on Matlab language to forecast 20# steel's corrosion behavior in Daqing oil field is built.

用基于Matlab语言的人工神经网络工具箱对从室内模拟埋片实验及现场调查得出的土壤腐蚀数据进行训练、仿真，从而建立了能够预测20#钢在大庆油田地区土壤中的腐蚀行为的网络模型。

A ramose input an d multi-output dynamic recurrent neural , network model RDRNN is presented in the , paper.

提出了一种多输入多输出分支动态递归神经网络模型，利用梯度下降法推导了网络权值调整公式。

This research has proved that an artificial neural network is capable to differentiate the reactional enhancement of malignant intracranial gliomas in postoperative MR images and the enhancement caused by tumor residual. As a innovative differentiation approach, it requires further studies and researches to determine its applicability in practice, including the increase of training samples, image description standardization, effects to doctoral diagnosis, as well as parameter optimization. With improvements in these elements, the performance of the network will be optimized.

本研究成功地证明了人工神经网络能够鉴别颅内恶性胶质瘤术后磁共振图像的反应性强化与肿瘤残存所致的强化，为解决二者的鉴别这一复杂问题提供了一个新的方法，但是本研究只是初步的应用探讨，能否在实际中应用，还有待于进一步的研究，如训练样本的增加、图像描述的规范化、对医师诊断影响程度、参数的优化等，网络的性能会不断完善和提高。

This research has proved that an artificial neural network is capable to differentiate the reactional enhancement of malignant intracranial gliomas in postoperative MR images and the enhancement caused by tumor residual. As a innovative differentiation approach, it requires further studies and researches to determine its applicability in practice, including the increase of training samples, image de脚本ion standardization, effects to doctoral diagnosis, as well as parameter optimization. With improvements in these elements, the performance of the network will be optimized.

本研究成功地证明了人工神经网络能够鉴别颅内恶性胶质瘤术后磁共振图像的反应性强化与肿瘤残存所致的强化，为解决二者的鉴别这一复杂问题提供了一个新的方法，但是本研究只是初步的应用探讨，能否在实际中应用，还有待于进一步的研究，如训练样本的增加、图像描述的规范化、对医师诊断影响程度、参数的优化等，网络的性能会不断完善和提高。

With the combination of artificial neural network, genetic algorithm, and immune system theory, the immune modulated symbiontic evolution method in neural network design is proposed.

引 言人工神经网络、进化算法和免疫网络算法是现代信息科学和生命科学相互交叉渗透的研究领域，它们都来源于自然界中生物的信息处理机制，并被用于构造能够适应环境长期变化的智能信息处理系统。

This paper presents a N-R method of acquiring multi-level reasoning production rules automatically based on NN, so as to resolve the bottle neckproblem in building a knowledge - based system-knowledge acquisition. This methodadopts a characteristic NN structure model and corresponding learning algorithm, so thatN -R method can fix the number of hidden nodes dynamically and form new conceptswhich are not defined in the sample set in the course of learning. Having been trained, NNis transforme...

本文为解决知识系统构造过程中的瓶颈问题──知识获取，提出了一种基于神经网络NN的自动获取多级推理产生式规则的N－R方法，该方法采用了特有的NN结构模型和相应的学习算法，使得NN在学习过程中动态确定隐层节点数的同时，也产生了样例集中没有定义的新概念，学习后的NN能用本文提出的转换算法转换成推理网络，最终方便地得到产生式规则集

The BP neural networks are used to improve remnant error model of GM (1,1) obtained forecast result carried on the combining forecast model which forecast again and has carried on the forecast to the vanadium titanomagnetite output of Pan zhihua.

这里介绍了灰色系统和BP神经网络相结合的预测原理，利用BP网络，对改进的GM(1，1)残差修正模型所得预测的结果进行再预测的组合预测模型，并对攀枝花市钒钛磁铁矿的产量进行了预测。

To enhance the monitor efficiency of optimization process, an efficient sensitivity analysis method based on the idea of orthogonal experiment is advanced, which is unlimited to specific algorithm and can be commonly used to discrete, underivable or implicit optimization problems.

在改进寻优算法方面，研究了基于Lagrange函数的适合于求解一般约束问题的神经网络模型算法，探讨了神经元非线性度和拉氏乘子等对优化效率的影响，提出了提高网络优化效率的控制策略。

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。