The Research of fast Neural Network training algorithm is taken attention at all times.
神经网络快速训练算法的研究一直是人们所关注的问题之一。
In addition, it does not require the time-consuming training process offline and saves the time of neural network training.
此外，它并不需要耗费的时间的训练过程中脱机并保存的神经网络训练的时间。
Based on this, we also adopt the adding mean quantization algorithm to improve the neural network training speed of image processing.
在此基础上又采用了加均值量化算法来提高神经网络图像压缩处理的训练速度。
The signal eigenvectors of vibration signal for the training were extracted by wavelet packet by the, and then used for neural network training.
对于用于训练学习的振动信号用小波包变换的方法对信号进行特征值提取得到信号的特征向量，并对神经网络系统进行训练。
In the end, we initially achieved the classification for Fusarium by optimizing BP neural network training targets, network structure and transfer function.
最后，对BP神经网络的训练目标、网络结构和传递函数等参数进行了优化，初步实现对镰刀菌的分类。
Once the neural network training has finished, it can diagnose not only the shown faults but also some faults never shown in some extent because of its fault tolerance.
由于其具有容错性，训练好神经网络不仅能诊断出已经出现过的故障，还能在一定范围内诊断出从未出现过的故障；
This algorithms has been widely used in machine learning, artificial intelligence, adaptive control, artificial neural network training, Image processing, among other areas.
目前这类算法已被广泛应用于机器学习，人工智能，自适应控制，人工神经网络训练，图像处理等各个方面。
A new mutual genetic operator based three stages feedforward neural network training method is proposed in this paper, which divides neural networks training procedure into three stages.
论文提出了一种新的基于互补遗传算子的前馈神经网络三阶段学习方法。该方法把神经网络的学习过程分为三个阶段。
Some problems such as the foundation of dynamic fictitious datum station, the neural network framework of fictitious datum station are discussed. The method of neural network training is described.
讨论了建立动态虚拟基准站的方法及基于神经网络的虚拟基准站的结构，并对这一神经网络进行了训练。
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.
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。
Taking cable tension indices as inputs of neural network for both training and testing, damage locations are indicated by the outputs of the network.
以不同损伤程度下斜拉索张力指标作为神经网络的训练与测试输入，由神经网络的输出来指示损伤位置。
The optimum programs are made for the target error, the learning of Neural Network, the time of training.
对目标误差、网络的学习率和训练次数进行了具体的优化。
The method uses wavelet transform and principle component analysis to preprocess fault signal, afterward training and testing wavelet neural network with the preprocessed fault characteristic data.
该方法首先利用小波变换和主成分分析对故障信号进行预处理，然后用处理后的故障特征数据对小波神经网络进行训练和测试。
Carries on the training through the use reasonable study algorithm, the neural network has to the thing and the environment very strong from the study, auto-adapted and from the organization ability.
通过利用合理的学习算法进行训练，神经网络对事物和环境具有很强的自学习、自适应和自组织能力。
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.
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。
Choosing a training method is very important when using neural network to obtain the model and the inverse model of the nonlinear object.
在使用神经网络完成非线性对象的模型和逆模型时，选择的训练方法很重要。
The introduction study rate speeds up the BP neural network the training speed.
引入学习率来加快BP神经网络的训练速度。
This paper applies parallel tangents of nonlinear programming during the weights training of neural network and puts forward a neural network in view of fast learning algorithm.
因此，作者将非线性规划的平行切线算法用于神经网络的权值学习，提出了一种具有快速学习算法的神经网络。
A structure and training algorithm for quasi-diagonal recurrent neural network (QDRNN) is presented.
提出一种准对角递归神经网络(QDRNN)结构及学习算法。
The results show the optimized BP neural network can effectively avoid converging on local optimum and reduce training time greatly.
实验结果证明，优化后的BP网络可有效地避免收敛于局部最优值，大大地缩短了训练时间。
Based on the powerful nonlinear reflection and training function of artificial neural networks, the model of BP neural network for foundation piles integrity testing is put forward.
利用人工神经网络强大的非线性映射能力和学习训练功能，提出了基于BP网络的基桩完整性检测模型。
This mapping relation is determined by training neural network with a back-propagation algorithm, which is utilized to estimate images at finer resolution from coarser versions.
使用反向传播算法训练神经网络，确定这种映射关系；根据该映射关系由低分辨力图像估计高分辨力图像。
There exist over learning and the difficulties of selecting suitable parameters when training neural network.
在神经网络的训练当中存在“过学习”现象以及参数难以选择的困难。
Theoretical analysis, choice of fault characteristics and practical procedure of neural network setting and training are given out.
给出了该方法的理论分析，故障特征量的选取，神经网络设置和训练的具体步骤。
The algorithm is tested by two generally used functions and is used in training a neural network for image recognition.
该算法经两个常用函数检验，并在图象识别的神经网络权值训练中得到应用。
Method the artificial neural network and the advanced BP training arithmetic operations based on momentum factor technique are used.
方法采用人工神经网络方法和基于动量因子技术的改进BP网络训练算法。
The characteristic parameter extraction, the neural network architecture and the network training are given.
文中介绍了特征参数的提取、神经网络的构成以及训练方法。
The initial weights and biases of the artificial neural network(ANN)are obtained by offline training method.
人工神经网络（ANN）的初始权值和阈值通过离线训练的方式获得。
The initial weights and biases of the artificial neural network(ANN)are obtained by offline training method.
人工神经网络（ANN）的初始权值和阈值通过离线训练的方式获得。
应用推荐