收敛速度

混合激活函数对BP算法收敛速度的影响

Effects of Combined Activation Function on BP Algorithm 's Convergence Speed

提高BP小波神经网络收敛速度的研究

Study on Improvement of Convergence Speed for BP Wavelet Neural Networks

在网络训练过程中采用改进的BP算法，通过对学习算子的优化搜索，大大提高了网络的收敛速度，解决了BP算法迭代过程中目标函数振荡问题。

The modified BP algorithm is presented by optimization of leaning step-size .

采用了改进的BP学习算法，以提高训练的收敛速度。

In order to improve training speed , improved back propagation algorithms are adopted .

针对普通BP算法存在的收敛速度慢以及容易陷入局部极小点等问题，提出了一种改进的BP算法，应用该算法对空调系统传感器故障进行诊断。

An improved BP algorithm was presented and applied it to sensor fault diagnosis of air-conditioning unit .

研究BP算法中激励函数f对收敛速度的影响，并对其进行了修正。

The influence of activation functions in BP algorithms is studied , and trying to amend it .

和标准BP网络相比，提出的3种改进模型都具有收敛速度快、精度高的优点。

Compared with standard BP network , all of improved models have advantages faster convergence speed and higher efficiency .

由于协方差对加性脉冲噪声的敏感性，传统的各种MUSIC算法会出现不同程度的退化，且收敛速度较慢。

Because covariance is sensitive to additive impulsive noise , conventional MUSIC algorithms become degenerative to various degrees and the convergence rate is slow .

实验结果表明，这种基于模糊B样条基神经网络的磁共振图像分割方法与普通神经网络分割方法相比，具有更高的分割精度和更快的训练收敛速度。

The results of experiments show that the proposed method has better segmentation precision and faster network convergence speed than traditional neural network segmentation method .

Beta算子收敛速度的下界估计

Lower estimates of convergence rate for Beta operators

BP算法训练神经网络具有训练易陷入局部极小，收敛速度缓慢的缺点。

BP ( Back Propagation ) algorithm has some defects , such as converging slowly and immersing in local vibration frequently .

针对BP神经网络应用中存在的训练时间长、收敛速度慢的问题，对常用的BP神经网络方法进行了改进，增加了数据前处理和后处理的过程。

An improved method was proposed in order to accelerate the convergence speed and shorten the training time of BP neural network .

该学习算法的收敛速度比BP学习算法快，且比并行递推预测误差学习算法有更好的数值稳定性。

It has better convergence than the back propagation learning algorithm and better stability than the parallel recursive prediction error learning algorithm .

文中采用了改进的模糊C均值聚类算法，对隶属度矩阵进行了修正，加快了聚类的收敛速度；

An improved fussy C mean clustering algorithm was used , in which the matrix of grade of membership was modified in order to speed up convergent velocity .

关于Taylor定理的中值的渐近性与收敛速度

On the Asymptotic Approximation and Asymptotic Rate of Convergence of the Mean Value of Taylor Theorem

然而，在实际运用过程中，BP神经网络具有收敛速度缓慢，容易陷入局部极小的缺陷。

However , the BP neural network has slow convergence speed and is easy to fall into local minimum problems in practical application .

ACS针对AS在构造解过程中算法收敛速度慢的缺点进行了改进。

ACS overcomes the disadvantage of slow convergence rate in solution construction process .

研究了手写体汉字识别技术，采用改进BP算法进行网络训练，提高了算法的收敛速度。

A technological research on recognition of handwritten Chinese characters based on improved BP algorithm is summarized . This algorithm can enhance convergence speed .

在ACS基础上，改良的蚁群算法采用了更为高效的信息素更新和路径选择机制，使得改进后算法的全局收敛速度得到明显的提高；

The improved ant colony optimization algorithm is using a new pheromone updating strategy .

对于传统BP算法存在的收敛速度慢和易陷入局部极小值问题，人们提出了径向基函数网络。

People put forward radial basis function networks considering the conventional BP algorithm problems of slow convergence speed and easily getting into local dinky value .

可以知道CCA算法的收敛速度比传统算法的收敛速度快。

CCA algorithm convergence rate is faster than traditional algorithms convergence .

证明了新算法等价于Newton迭代法并且有二阶收敛速度。

And it is proved that it is equivalent to Newton iterative algorithm and has second order convergent speed .

MATLAB仿真证明，该算法的收敛速度很快，通常迭代四、五次即可收敛，并且可以达到很高的精度。

The MATLAB simulation result shows that the convergence speed of this algorithm is very fast , iteration is about four or five with high accuracy .

PSO算法本质上属于迭代的随机搜索算法，其主要优点在于收敛速度快、能以较大的概率找到优化问题的全局最优解等。

PSO being iterations random algorithm does better in fast constringency and finding the optimization solution with biggish probability .

结果表明，所提出的算法在收敛速度等方面大大优于通常的BP（反向传播）算法、带动量项的BP算法以及其他的一些改进的算法。

The results show that the proposed algorithm improves considerably on the convergence speed of the general back-propagation algorithms , including when using momentum , and other improved algorithms .

利用改进的BP网络和RBF网络进行了短期电力负荷预测，并对训练的收敛速度和预测精度进行了分析。

By the improved BP and RBF neural networks , short-term electric load is forecast and training ( convergence ) rate and forecasting precision are analyzed .

对于gcg的收敛速度，尺度矩阵H的形成具有重要作用。

It is found that the matrix H plays an important role in the descent rate of gcg .

为了克服BP神经网络自身算法的缺陷，得到更高的学习精度和更快的收敛速度，该文建立了基于遗传算法的小波神经网络电价预测模型。

In order to avoid the limitation of the BP neural networks , this paper establishes the electricity price forecasting model using wavelet neural networks based on the genetic algorithm .

由于PSO的收敛速度快，设置参数少，操作更方便，是一种高效的优化搜索方法。

As PSO is fast in convergence rate , few in parameter setting and easy in implementation , is an efficient search algorithm .

模拟实验表明，改进后的REM算法队列十分平稳，收敛速度比原来的算法快，适用于高带宽网络。

The simulation experiments showed that the improved REM algorithm had stable queue and was faster convergent than REM.