查询词典 neural

In this pape r, we discuss some problems of feedforward neural networks. A mathematical theory is introduced for the feedforward neural networks.

摘 要 讨论了目前前馈神经网络研究中存在的一些问题，给出了前馈神经网络的一种数学框架。

After analysis and parison of virtues and hort ings of existing systemsafety evaluation ways, Artificial Neural Network, Artificial Intelligence and Expert System are used to build new system safety evaluation means. System safety evaluation model and intelligent expert system for fault diagnosis based on ANN have been put forth. Development and realization of visual neural network for system safety valuation and fault diagnosis provides new idea for system safety evaluation and accident mode diagnosis.

对已有的系统安全评价技术方法的优缺点进行了分析和对比，继而将神经网络技术、人工智能技术、专家系统应用于开发新的系统安全评价方法，提出了基于人工神经网络的系统安全评价方法和基于神经网络的智能故障诊断专家系统模型，开发了可视化的神经网络系统，为系统安全评价与事故模式诊断提供了新思路。

At 2 weeks following injury, hematoxylin-eosin staining showed that brain tissue breakage at damaged site as scar connection, remarkable porosis in the blank group; typical morphological changes as neural cells at the transplanted site in the control group; typical morphological changes as neural cells without cavity in the experimental group.

伤后2周苏木精-伊红染色空白组可见损伤处脑组织断裂，为瘢痕连接，有明显空洞形成；对照组在移植部位出现典型的神经细胞样形态学改变；实验组出现典型的神经细胞样形态学改变且空洞消失。

In particular, it is unknown how the relevant neural substrates function as a network to mediate perspective-taking during the task requiring understanding other's belief. The current work first developed a new psychological paradigm that excludes potential confounds such as the processing of language, biological motion, episodic memory and causal coherence in the paradigms used in previous studies. I recorded neural activities associated with mental inference task using functional magnetic resonance imaging and electroencephalography in order to investigate the functional roles of several brain areas (i.e. precuneus, MPFC, etc.) that engage in understanding other's belief. I also proposed a computational model based on the neuroimaging results that simulated the neurocognitive mechanism underlying cortical dynamics in correct judgment of other's belief.

本文首先发展了一个新的心理学实验范式，排除以往常用&错误信念&范式中与语言加工、生物运动、情景记忆及事件连续性和因果性等方面的混淆，采用功能磁共振成像（functional magnetic resonance imaging， fMRI）和脑电（Electroencephalography， EEG）时频分析等脑成像技术，记录与理解他人信念任务相关的神经活动，通过对行为和脑成像数据的分析，研究楔前叶和内侧前额叶等脑区在理解他人信念任务中的功能意义，并根据脑成像结果，提出一个基于自我和他人视角竞争的计算模型，模拟大脑在理解他人信念时做出正确决策时的认知神经机制。

The patients were followed up for 22.2 months. There were no obvious loss of correction, trunk equilibrium or pseudoarthrosis. No worsened neural symptoms or new irreversible neural functional lesion were found.

术后平均随访22.2个月，无明显矫形丢失、躯干失平衡、假关节形成，且未发生原有神经症状加重及新的不可逆性神经功能损害。

To find more suitable extraction algorithm for neural net recognizers, the applications of LPC sepstrum as well as the RW are investigated, and new procedures for the vector alignment and the normalization are proposed. The Time-Delay Neural Net model is generalized, and two kinds of non-uniformly windowed-time-windowed and component-windowed -pyramidical architectures are proposed.

为寻找比较适合于神经网络识别器的特征提取方法，文中研究了RW法和LPC倒谱系数特征提取法在神经网络中运用，并提出了一种新的时间对准和向量规整的方法；推广了时延神经网络模型，提出时间划分和分量划分两种加非均匀窗的金字塔状结构。

The tight wavelet neural network was constituted taking the nonlinear Morlet wavelet radices as the stimulant function. The idiographic algorithm was presented. It can combine the advantages of wavelet analysis and neural networks.

以非线性Morlet小波基作为激励函数，形成神经元，结合小波变换与神经网络各自的优点，建立集小波分析与神经网络于一体的紧致型小波神经网络，并给出了具体的算法。

Fuzzy neural network is used in the three phase adaptive reclosure so that the reclose of permanent faults can be avoided. A multi-input fuzzy neural network is constructed and the algorithm of network is designed. Taking the virtual value of three phase voltage as the input with its scale changed, the network learning can be completed with convergence reached after the process of fuzzification, normalization and perspicuity, so it can disinguish transient faults from permanent faults.

为了避免重合闸重合于永久性故障，将模糊神经网络应用于三相自适应重合闸中，构造了一个多输入的模糊神经网络，设计了网络的算法，将三相端压有效值作为输入，经尺度变换、模糊化、归一化和清晰化，并利用梯度下降法修正误差，使得网络完成学习并最终收敛，在输入故障数据时能根据网络的输出结果准确地判别瞬时性故障与永久性故障。

The neural network is used to identify a nonlinear system. Based on the resuIt of system identification, a neural controller of the nonlinear system can be obtained.

首先以类神经网路来描述系统动态特性，其次再利用此系统鉴定模式来设计一适当的类神经控制器。

In this part, the author advanced a new neural network model for natural language processing, Seme neural network model, and applied it to the experiment of matching the nouns and classifiers in chinese.

本文的第四章针对微型储能装置在保护敏感负载的应用，提出了多重化移相式单象限斩波器结构，并对该结构进行了分析和仿真。

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。