结合均匀设计和聚类思想提出的样本优选方法，在一定程度上解决了神经网络样本选择的问题。
Based on uniform design and the cluster theory, a optimum selecting method of sample is proposed to solve the problem of sample selection.
同时，将诊断输出值引入网络样本库，组成了自适应智能诊断系统，提高了故障诊断结论的准确性。
Meanwhile, the diagnosing result was introduced network sample database to construct self-adaptive intelligent diagnosing system, thus, the accuracy of malfunction diagnosis improved as a result.
为确保对暴发的准确追踪，网络成员也在使样本采集、检测和结果解释的方法标准化。
To ensure accurate tracking of the outbreak, members of the network are also standardizing methods for sample collection, testing, and the interpretation of results.
当你在设计一个网络应用程序的时候，不仅用样本数据进行测试是重要的，而且确保在没有数据的时候看起来也是好的和有用的，显得同样重要。
When you're designing a Web application, it's important not only to test it with sample data, but to ensure that it looks good and is helpful when there is nothing there yet.
生产计划的样本在网络上和一些医疗机构那里都是可以得到的。
Sample birth plans are available on the web and from some healthcare providers.
迄今为止，向世卫组织的网络实验室提交了2.3万份以上的病毒和其它样本供分析。
To date, well over 23,000 viruses and other specimens have been submitted to WHO network laboratories for analysis.
一个能够完成这些切割的网络同样可以识别源代码样本中的语言。
A net that could make these cuts could also identify the language of a source code sample.
通过主成分分析法将众多指标进行综合，消除样本间的信息重叠，降低BP网络的输入维数。
Through principal component analysis, we have synthesized numerous indexes, (eliminated) information overlapping of the sample, and reduced the input dimension of BP network.
试验结果表明该方法是有效、可行的，且在小样本情况下比BP神经网络具有更高的诊断精度。
The test shows that this method is effective and feasible, and has higher diagnosis precision than BP neural network in cases of fewer samples.
首先利用测振传感器获得转子的振动信息，然后用FFT分析，将振动信号的频谱分析作为神经网络的训练样本。
The dynamic vibration information is gained from acceleration meter, and then by FFT analysis, the frequency information of vibration is used as the training specimen of neural network.
中国卫生部已经决定将样本送交世界卫生组织国际确证实验室网络中的实验室进行检验。
The Ministry of Health of China has decided that samples will be sent to a laboratory that is part of the WHO international reference network.
以保定市各县供电企业专家评价数据作为BP神经网络的训练样本，进行仿真试验，得到了满意的结果。
Simulation tests were carried out with evaluation data given by experts from power supply enterprises in Baoding taken as training samples for BP neural network, and the results are good.
应用人工神经网络方法，以航磁数据为样本，建立了航磁信息关联的BP人工神经网络模型。
Based on the application of artificial neural network principle, this paper presents a BP artificial neural network model for aeromagnetic information connection.
前向网络利用反向传播算法训练多层网络，使训练后的网络较好地拟合样本空间中各点的函数值。
Feedforward networks use back propagation algorithm to train a multi-layer network. After training, the multi-layer network can fit the function in the data space very well.
BP网络训练样本由有限元模型模态分析所得。
BP network train sample mode analyse the income by finite element model.
通过选择足够的故障样本来训练神经网络，将代表故障的信息输入训练好的神经网络后，由输出结果就可以判断发生的故障种类。
When symptoms that represent faults are input to the trained neural network, the type of fault can be determined in the output of the neural network.
该软件包括大量的网络项目任务细节方案收藏以及模板，样本和简单易用的向导。
The software includes large collections of task-specific shapes of network objects as well as templates, samples, and easy-to-use wizards.
神经网络的数学算法可将样本的输入输出转变为非线性优化算法。
Mathematical algorithm in nerval network can change the input and output of a sample into nonlinear optimal algorithm.
人工神经网络可以从一组样本中学习。
An artificial neural network can learn from a set of samples.
改进了神经网络模型的算法，使其在样本数据相对较少的条件下也能很好地在性态上模拟被逼近函数。
The Neural Networks models is improved, it can simulate the approached function commendably even at the case of the little number of the samples.
提出了BP网络分类器的设计方法、样本的选择及组织方法。
The method of BP network classifier design, the way of sample selection and organization are both delivered.
在神经网络负荷预测实际应用中，突出的问题是训练样本大、训练时间长、收敛速度慢。
In application of neural networks based short-term load forecasting model, the main problems are over many training samples, thus resulting long training time and slow convergence speed.
然后介绍了如何使用模糊聚类算法和等价的前馈神经网络从样本数据中辨识离散的TS模型。
Then we introduce how to identify the TS model from sample data using fuzzy clustering algorithm and equivalent feedforward neural network.
采取运行机理建模和神经网络建模相结合的方式，把输入样本空间进行划分，实现基于混合专家网络的建模。
In the new method, input samples are divided into sub-space and hybrid expert neural networks model is realized.
然后通过教师样本数据对网络进行充分的训练，获得适宜的参数矩阵；
Second train the network well though training-samples and obtained the best network parameters vector.
将融合后的最终结果输入到高阶BP神经网络中，通过目标向量样本的训练，输出相应的目标类型。
Then the final results into the high order BP network is input. Through the training of target vector table stylebook, corresponding type of goal can be output.
最后利用优化后的网络对未来的股指(测试样本)进行预测。
At last the test samples were predicted by the ultimate network.
该系统主要由以下模块构成：用户界面模块、网络模型模块、样本处理模块、神经网络计算模块以及神经网络训练结果显示模块。
The system consists of graphic user's interface module, sample processing module, neural network structural module and neural network computing module.
该系统主要由以下模块构成：用户界面模块、网络模型模块、样本处理模块、神经网络计算模块以及神经网络训练结果显示模块。
The system consists of graphic user's interface module, sample processing module, neural network structural module and neural network computing module.
应用推荐