神经网络

Conventionally the electric load forecasting can hardly attain a result whose accuracy meets what's required. A short-term load forecasting model is therefore developed to solve the problem, based on the process neural network of which the input is the function of time and the high forecasting accuracy is available. Describes the structure of the model, discrete data fitting method by the expansion of function orthogonal basis and learning algorithm.

针对目前常用方法在解决负荷预测问题时，结果往往难以达到工程要求精度的现状，利用过程神经网络输入为时间函数以及预测精度高的特点，建立了基于过程神经网络的电力系统短期负荷预测模型；给出了模型的结构，基于函数正交基展开的离散数据拟合方法以及模型的学习算法。

In order to simplify the algorithm, orthogonal functions are selected as base functions, and the effectiveness of the model and the algorithm is proved by simulation of oil reservoir exploitation.

过程神经网络是人工神经网络在时间域上的一种扩展，从而使问题更为一般化。对于求解与过程有关的众多实际问题有较好的

The structure of the orthogonal function neural network is first introduced, and then, the principle of orthogonal neural network is analyzed by using Chebyshev orthogonal polynomials.

首先，本文提出了正交函数神经网络的网络结构，分析了利用Chebyshev正交多项式形成神经网络的机理。

In this paper, a new kind of two-dimensional Cellular Automata is studied. Several algorithmic rules are discovered that can be used to design new Cellular Neural Networks which can implement shadow detector and overstriking for character recognition. Their Boolean expressions and learning algorithms are introduced detailedly.

摘要该文深入研究了一种新的二维细胞自动机，找到了几种新的算法规则可以用来实现字符的粗化处理和阴影检测，并且用这些规则设计了几种新的细胞神经网络，文中详细介绍了这些算法规则的布尔代数表达式和细胞神经网络学习算法。

The training problem is cast as optimization problem in parameter space.

其方法实质是将神经网络的训练问题转化为优化问题，利用禁忌搜索算法的全局寻优能力获得最优的神经网络权值与阈值。

The optimal control problem for the FCC process is solved using the MFNN (multilayer feedforward neural network) for system recognition and modeling, periodogram analysis for model testing, and the advanced Frank-Wolfe algorithm for steady state optimization computation.

为解决催化裂化过程的优化控制问题，采用多层前馈神经网络进行辨识、建模，用周期图检验法对模型检验，用改进的Frank-Wolfe算法进行稳态优化计算，并以大港炼油厂实际生产过程的稳态数据进行试验和验证，说明神经网络适合于解决非线性复杂生产过程的辨识、建模和稳态优化控制问题。

Finally, during the period of Ph D.

故障诊断的模块化神经网络也是提高神经网络诊断精度的一个有效途径。

KEY WORDS: Artifical neural network, pharmaceutic analysis, traditional chinese medicine, pattern recognition, QSAR, experiment optimization

把人工神经网络引入到实验结果的回归之中，采用人工神经网络优化实验条件，建立了实验方法设计和回归系统，提高了实验设计系统的智能水平，为进一步的实验设计专家系统研究奠定了基础。

Based on the previous works, the paper first introduced and summed up the princi ples and characteristics of information processing of ANNs. Then the paper placed em phasis on their algorithms and theory foundation of application for operator approxima tion and patern recognition to lay the theory base for the study of the data-driven joint inversion.

在前人研究的基础上，本文首先归纳和总结了人工神经网络的基本原理和信息处理特征，并着重讨论了BP神经网络的算法原理和它在估计映射算子和模式识别方面应用的理论依据，为本次数据驱动的联合反演研究奠定了理论基础。

To improve the convergence efficiency of neural network in color space conversion of digital photofinishing, an adaptive optimization model based on BP neural network was designed.

为了提高神经网络在数码冲印颜色空间转化应用中的收敛效率，设计了一种基于反向传播神经网络的自适应优化模型。

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。