The result shows that the parallel BP algorithms is effective.
结果表明，该并行BP算法十分有效。
Based on optimized BP algorithms, some prediction models are developed for cement strength.
运用改进的BP算法，建立了水泥强度预测模型。
An effective network learning method is formed by combining GA, BP algorithms with fuzzy logic system.
将模糊逻辑系统、GA算法与BP算法相结合，形成一种有效网络学习方法。
Aim To study the standard BP algorithms local minima and learning speed problems and propose the scheme for improvement.
目的对BP学习算法中存在的大量局部极小点以及收敛速度慢问题进行研究并提出相应的改进方案。
This paper puts forward a model of discovering and forecasting price trend in market, based on neural networks BP algorithms.
提出了一种利用神经网络BP算法模型于发现和预测商业市场价格变化趋势的模型。
This paper discusses how to predict the reliability of products in storage with the method of BP Algorithms which is widely used in some other fields.
本文通过在其他领域应用广泛的神经网络BP算法，对库存的物品的可靠性进行评估。
On the basis of evolutionary neural network, the recognition model of promoter in eukaryote's gene was built using BP algorithms and genetic algorithms.
所以在此基础上，利用进化神经网络，采取BP算法和遗传算法建立了真核生物基因启动子识别模型。
To eliminate the shortcoming of standard backpropagation algorithm, some modified BP algorithms in the MATLAB's neural networks toolbox are given in the paper.
针对标准BP算法存在的缺陷，本文给出了基于MATLAB语言的BP神经网络几种改进的算法。
In this paper we prove a finite convergence of online BP algorithms for nonlinear feedforward neural networks when the training patterns are linearly separable.
当训练样本线性可分时，本文证明前馈神经网络的在线BP算法是有限次收敛的。
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。
Through computer simulation, samples, BP algorithms and the influence of network structure neurula on model performance have been discussed as well as the improving measures.
通过计算机实验，讨论样本、学习算法和网络结构等对神经网络预测模型性能的影响及其改进措施。
In this paper, the characteristic and performance of various fast BP algorithms are generalized and contrasted through study on simulation of nonlinear function approximation experiment.
对几种快速BP算法的特点及性能作了归纳和对比，并对一个非线性函数逼近实例进行了仿真研究。
The improved BP algorithms based on adaptive parameters adjustment and error contracting gradually are presented, which are applied successfully to fault diagnosis of steam- turbine generator unit.
提出了自适应学习率及动量因子的BP神经网络算法和误差逼近度渐近收缩学习的BP神经网络算法，并将其应用于汽轮发电机组振动故障诊断与识别。
Based on expatiated the basic structure model and some general improved algorithms of BP neural network, this paper brings forward a new self-organization learning algorithm.
介绍了BP网络的基本结构模型与常见改进算法，在此基础上提出了一种新型的结构自组织BP网络算法。
Based on adaptive LMS algorithms, the on line BP algorithm with fast convergence speed is presented.
在自适应LMS算法基础上，提出了在线BP训练算法、收敛速度快。
BP algorithm is one of the most widely used algorithms in neural network.
BP算法是神经网络中最常用的算法之一。
A new method ameliorating the calibration accuracy for flowmeter that is based on BP network - (genetic) algorithms (GA) is proposed.
提出一种基于神经网络(BP)-遗传算法(GA)的高精度流量仪表标定方法。
The thesis introduces some ANN design algorithms, which are BP algorithm, FP algorithm, alternative covering design algorithm of multi-layer neural networks.
文中介绍了目前使用的几种不同的人工神经网络设计算法：BP算法、FP算法、多层前向网络的交叉覆盖设计算法。
By a theoretical derivation of BP and RM algorithms, the algorithms are the same on principle.
通过对BP算法和RM算法的理论推导，从原理上说明了两种算法的一致性。
The known study algorithms which are used to be Fuzzy Neural Network parameter study algorithms are BP algorithm with gradient descent and inheritance algorithm.
目前使用的最多的学习算法仍然是基于梯度下降的BP算法和遗传算法。
Several traditional algorithms used in traffic incident detection are reviewed. A detection model based on artificial neural network is proposed and implemented with BP algorithm.
回顾几种传统的交通事件检测算法，提出从多层前向人工神经网络角度建立模型，并运用BP算法予以实现。
There are a few training algorithms for parameter estimation of neural networks, in which Back Propagation(BP)algorithm is the typical algorithm for feed-forward multi-layer neural networks.
神经网络参数估计有许多训练算法，BP算法是前向多层神经网络的典型算法，但BP算法有时会陷入局部最小解。
The paper used the Bayes regularization algorithm to train the BP network, the precision and generalization of which are better than the network that uses ordinary training algorithms.
本文采用贝叶斯规则化的训练方法，训练好的BP网络较常用的训练方法具有更好的精度和泛化能力。
Combined Genetic Algorithms (ga) and back-propagation neural network (BP), an optimized GA-BP model was established to predict phosphorus content. Some data were chosen to train the network model.
结合遗传算法(GA)和误差反馈型神经网络(BP)，建立了优化的GA - BP神经网络预测模型，预测转炉炼钢过程钢液终点磷含量。
The problem of trapping into the local minimum is solved, which is inherent with the learning algorithms-based on the BP principle by weight strategy.
但是BP网络极容易陷入局部极小（值），应用加权策略解决了此问题。
The results shows that the forecasting effect of the new algorithms is better than the BP neural networks.
结果表明，改进方法的预测效果优于单一使用BP神经网络进行预测的效果。
Sinter quality simulating model and optimizing iron ores matching model were built by using BP neural network technology and genetic algorithms technology, respectively.
应用BP神经网络技术和遗传优化技术分别建立烧结矿质量模拟模型和烧结寻优配矿模型；
Sinter quality simulating model and optimizing iron ores matching model were built by using BP neural network technology and genetic algorithms technology, respectively.
应用BP神经网络技术和遗传优化技术分别建立烧结矿质量模拟模型和烧结寻优配矿模型；
应用推荐