The simulation result shows that the algorithm has much faster learning speed compared with the standard BP algorithm. It is entirely practicable in diesel fault diagnosis system.
仿真结果表明，该算法比标准BP算法具有更快的学习速度，完全适用于柴油机故障诊断系统。
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。
The learning algorithm is BP (Back Propagation) algorithm.
学习算法为反向传播算法。
To synthesize the advantages of standard BP algorithm and "batch learning" BP algorithm, a new algorithm is put forword.
综合了标准BP算法与“批处理”BP算法的各自特点，提出了一种新的BP网络的学习算法。
The new algorithm, compared to the BP algorithm, has the fast learning rate and good convergence properties.
该算法有效地改进了神经元网络的学习收敛速度，取得了比常规BP算法更好的收敛性能和学习速度。
Based on analysing characteristics of error curved surface of the network, the authors have advanced the rapid BP algorithm, which can greatly raise the learning speed.
通过分析网络误差曲面特征，提出了快速BP算法，它可以大幅度地提高学习速度。
Because of defects of BP algorithm, a hybrid learning algorithm is applied to train and optimize the network parameters.
针对BP算法的不足，使用混合学习算法训练网络，优化了网络参数。
In this paper, we proposed a parallel BP neural network learning algorithm with the support of PC cluster under the circumstance of PVM (parallel Virtual Machine).
本文提出了一种利用微机机群来实现并行处理，在并行编程环境P VM中实现BP神经网络的并行学习算法。
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。
Since we value the learning effect of neural networks by cumulative error, the paper pay direct attention to it to study the BP algorithm.
由于评价人工神经网络最终学习效果是通过累积误差来进行的，从而我们直接瞄准累积误差来研究多层人工神经网络快速学习的算法。
Though choosing the experimental results as the learning sample, the performance predictive model of EDM micro-and-small holes is proposed, with the BP algorithm of artificial neural network.
采用人工神经网络的BP算法，以电火花微小孔加工工艺参数正交实验的结果作为神经网络的学习样本，建立电火花微小孔加工多目标工艺参数的预测模型。
A new dynamic learning algorithm is proposed to overcome the shortcoming of traditional BP net learning algorithm.
针对传统的BP网络学习算法的缺陷，研究一种动态学习算法。
Finally, taking data from CAE as samples; the BP neural network of warping-shrinkage prediction model is established by designing the network structure and selection of learning algorithm.
最后以数值仿真得到的数据为样本数据，通过设计网络结构和选用学习算法，建立并得到基于BP人工神经网络的翘曲——收缩预测模型。
Finally, the MBP algorithm is compared with the standard BP algorithm. The results shown that the learning speed of MBP algorithm is increased greatly.
最后将标准BP算法和MBP算法进行了比较，仿其结果表明：MBP算法的学习次数和收敛速度得到极大改善。
The simulation result indicates that the algorithm has much faster learning speed and more superior learning precision compared with the standard BP algorithm.
仿真结果表明：该算法比传统的BP算法具有更快的学习速度和更高的学习精度。
Based on the idea of standard back-propagation (BP) learning algorithm, an improved BP learning algorithm is presented.
在标准反向传播神经网络算法的基础上，提出了一种改进的反向传播神经网络算法。
To accelerate the training speed of BP network, a joint-optimized fast BP learning algorithm is proposed.
针对BP网络学习速度的缓慢性，本文提出了一种联合优化后的快速学习算法。
Meanwhile, the back propagation learning algorithm is given based on BP.
文章还推导了基于BP的反传学习算法。
The GA-BP learning algorithm of neural network, the GA learning algorithm, the rule of optimum control including their features were introduced.
给出了作为模型预估器的神经网络GA—BP算法流程及GA 算法实现， 提出了最优控制指标选择原则及控制指标表达式。
Learning algorithm is the core of the subject of studying BP feedforward neural networks.
学习算法是BP前馈神经网络研究中的核心问题。
Analyzing the integral splitting PID algorithm, and melting the wide-used PID controller and the automatic learning neural network, got a PID control algorithm based on the BP network.
分析了积分分离pid控制算法，在此基础上，将应用最广泛的PID控制器与具有自学习功能的神经网络相结合，得到了基于BP神经网络的PID控制算法。
Concerned with the training process and accuracy, the LM algorithm is superior to conjugate gradient algorithm and a variable learning rate back propagation (BP) algorithm.
就训练次数与精确度而言，它明显优于共轭梯度法及变学习率的BP算法，适用于系统辨识。
The algorithm is applied to XOR problem and nonlinear function approximation. Simulation results show that the chaos-BP algorithm needs shorter learning time than that of the standard BP and fast BP.
采用混合算法对XOR问题和非线性函数进行仿真，结果表明该算法明显优于标准BP算法和快速BP算法。
The parameters of the fuzzy neural network controller are optimized by the mixed learning methods with BP algorithm and Simulated Annealing algorithm which improves BP algorithm.
该系统的控制器采用模糊神经网络控制器，它的控制器参数采用模拟退火算法全局优化来对BP算法进行改进的混合方法。
Compared to the standard BP, this algorithm integrated the additional momentum method with the adaptive learning rate method.
与标准BP算法比较，该系统通过结合附加动量法和自适应学习速率形成新的BP改进算法。
The imitation of computer proves that BP G S algorithm may decrease learning time in the whole. The effect is obvious especially when the error value is near to the optimal point.
文章最后的计算机仿真说明BPGS总体上可以减少学习的时间，尤其当误差值逼近最小点时效果明显。
The imitation of computer proves that BP G S algorithm may decrease learning time in the whole. The effect is obvious especially when the error value is near to the optimal point.
文章最后的计算机仿真说明BPGS总体上可以减少学习的时间，尤其当误差值逼近最小点时效果明显。
应用推荐