Traditional neural network algorithms are easy to fall into the local minimum, slow convergence when in fault diagnosis.
传统的神经网络算法应用于故障诊断时，具有易陷入局部极小值，收敛速度较慢等缺点。
Experimental study showed that as a local and whole conjunction neural network RBF network can be trained very quickly, and can overcome shortcomings of local minimum pole in BP networks.
通过实验研究，体现了RBF神经网络作为一种局部全连接网络，训练速度快，克服了BP网络的局部极小点问题。
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。
BP algorithm is the most popular training algorithm for feed forward neural network learning. But falling into local minimum and slow convergence are its drawbacks.
BP算法是前馈神经网络训练中应用最多的算法，但其具有收敛慢和陷入局部极值的严重缺点。
Combining grading method with chaotic optimization, the neural network model achieves rapid training and avoids local minimum when there are a lot of samples to be trained.
考虑神经网络在训练大规模样品时易陷入局部极小，用梯度下降法与混沌优化方法相结合，使神经网络实现快速训练的同时，避免陷入局部极小。
In this paper, an efficient engineering classification of ship noises based on a local adaptive wavelet neural network is presented.
提出了一种用于船舶噪声分类的局域自适应子波神经网络分类方法。
Aiming at the difficulties in modeling the complex MIMO system, the multilayer local recurrent neural network is used to build the predictive model of the process off-line.
针对复杂多变量系统难以建模的问题，采用多层局部回归神经网络离线建立其预测模型。
In this paper, fuzzy neural network was studied and fuzzy reasoning was realized by use of neural networks structure. BP algorithm is used to optimize local parameter.
本文研究了模糊神经网络，用神经网络结构进行模糊推理，用BP算法调节和优化具有局部性的参数。
Neural network BP training algorithm based on gradient descend technique may lead to entrapment in local optimum so that the network inaccurately classifies input patterns.
基于梯度下降的神经网络训练算法易于陷入局部最小，从而使网络不能对输入模式进行准确分类。
In order to prevent neural network learning from getting into local extreme point, artificial immune network algorithm was used to optimize neural network's parameters.
为了避免神经网络的学习过程陷入局部极值点，采用人工免疫网络优化神经网络的参数。
It is confirmed that PSO could overcome intrinsic shortcomings of BP neural network, including low learning efficiency, slow convergence rate, being easy to fall into local minima, etc.
经验证(PSO)优化算法可以有效地克服BP神经网络存在的学习效率低，收敛速度慢以及容易陷入局部极小点等固有缺点。
With this model, the initial weights and threshold values of the neural network are optimized using GA to avoid the possibility of local search minimum.
该模型采用GA对神经网络的初始权值和阈值进行优化，以避免可能的局部搜索最小现象。
Radial Basis Function Neural network is an effective feedforward network. It has high convergence rate and high approaching precision, and can avoid local optima.
径向基函数神经网络是其中的一类非常有效的前馈网络，具有收敛速度快、逼近精度高、可避免局部最小等优越性。
RBF neural network is a kind of local approximation neural networks. In theory, it can approximate any continuous function if there is enough neuron.
RBF神经网络是一种局部逼近的神经网络，理论上只要足够多的神经元，R BF神经网络可以任意精度逼近任意连续函数。
BP neural network, as its nature of gradient descent method, is easy to fall into local optimum.
但BP神经网络本质是梯度下降法，容易陷入局部最优。
The BP neural network has the ability to solve many practical problems because of its strong mapping. However, it has slow convergence rate and is prone to fall into local extremum.
BP神经网络具有很强的映射能力，可以解决许多实际问题，但同时还存在着收敛速度慢，易陷于局部极小的缺点。
CMAC neural network is a kind of local network with linear structure.
CMAC神经网络是一种具有线性结构、算法简单的局部逼近网络。
The self-adaptive learning rate and momentum coefficient are used to avoid the local minimum point in the training process of wavelet neural network.
小波神经网络的训练采用自适应调整学习率及动量系数的方法，以避免陷入局部极小值。
An improvement for dynamic fuzzy neural network (DFNN) was presented to avoid its running into the local extreme.
针对动态模糊神经网络(DFNN)在进行预测应用时容易陷入“局部极值”的缺陷，提出一种改进方案。
Optical implementation methods of one dimensional local interconnection neural network (LINN) for associative memory are proposed, and three optoelectronic system are discussed in this paper.
本文提出了一维局域互联关联存贮的光学实现方法，讨论了可用来实现局域互联网的三种光电混合系统。
The particle swarm optimization(PSO) algorithm, is used to train neural network to solve the drawbacks of BP algorithms which is local minimum and slow convergence.
针对多层前馈网络的误差反传算法存在的收敛速度慢，且易陷入局部极小的缺点，提出了采用微粒群算法（PSO）训练多层前馈网络权值的方法。
CMAC (Cerebellar Model Articulation Controller) is a kind of local learning feed - forward neural network with simple architecture, quick learning convergence and effective implementation.
小脑模型清晰度控制器(CMAC)是一种局部学习前馈网络，结构简单，收敛速度快，易于实现。
At present, there are three models of the neural mechanisms for temporal cognition: the specialized timing model, the distributed network timing model and the local timing model.
当前对时间认知的脑机制探讨有三个模型：特异化计时模型、分布网络模型和定域计时模型。
An improved BP neural network is proposed for the purpose of overcoming the slow convergence and existence of local minimum in conventional BP neural network.
先对传统的BP人工神经网络进行了分析，针对其收敛速度慢，存在局部极小值的缺点提出了一种改进后的BP人工神将网络。
A modified BP algorithm of neural network, random adjustment of parameters (RMBP) algorithm, is proposed to overcome the defect of easy going into local minimum of BP neural network.
针对BP(反向传播)神经网络学习易陷入局部极小的缺陷，提出了一种改进BP神经网络学习算法——RMBP算法。
The method makes the neural network be self adaptive and difficult to become the local minimum, so that the convergence rate can be greatly speeded and the learning time shortened.
该方法使网络具有自适应能力，从而不易陷入局部最小，导致收敛速度大大加快，训练时间大大缩短。
The method makes the neural network be self adaptive and difficult to become the local minimum, so that the convergence rate can be greatly speeded and the learning time shortened.
该方法使网络具有自适应能力，从而不易陷入局部最小，导致收敛速度大大加快，训练时间大大缩短。
应用推荐