The experimental results show that the network learning speed can be increased and the nonlinear errors of the sensors can be reduced by using BPNN.
实验结果表明采用BP神经网络可以提高网络收敛速度，大大减小传感器线性误差。
With the study of neural network model, this paper advances some of improvement and optimization techniques that can accelerate the learning speed of network and increase the stability of model.
本文从神经网络模型的结构出发，对学习算法提出了一系列改进和优化措施，以加快网络的学习速度，并增加模型的稳定性。
The application of additional momentum and adaptive learning rate overcomes the limitation effect of BP rule, accelerates the training speed and strengthens the generalization ability of network.
由于采用附加动量项和自适应率等措施，克服了BP规则的局限性，加快了训练速度，增强了网络的泛化能力。
General regression neural network is proved with certain superiority in the ability of approaching, classification and learning speed.
广义回归神经网络在逼近能力、分类能力和学习速度方面具有较强优势。
The algorithm can remove redundant link even nodes on the network, through the network learning step dynamic adjustment to avoid convergence speed of.
该算法能够删除掉冗余的连接甚至节点，通过对网络学习步长的动态调整，避免了算法收敛速度过慢和反复震荡的问题。
Experiment shows neural network classifier that is optimized by algorithm could not only have fast learning speed but also ensure accuracy of classification.
实验结果表明：算法优化后的神经网络分类器不但学习速度快，还能保证分类精度。
RBF neural network provides an effective means for system identification and modeling with its advantages of smaller calculation quantity and high learning speed.
RBF神经网络以其计算量小，学习速度快，不易陷入局部极小等诸多优点为系统辨识与建模提供了一种有效的手段。
The proposed learning algorithm can reduce the network sensitivity and keep the same convergence speed comparing with traditional learning algorithms.
次种学习算法与传统学习算法相比，可降低网络的灵敏度，但学习收敛速度基本相同。
For vector control AC drive system, the thesis presented a fuzzy neural network speed controller based on reinforcement learning.
针对矢量控制交流调速系统，该文提出并设计了一种基于再励学习的模糊神经网络速度控制器。
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。
By using CMAC neural network based on credit assignment this algorithm is implemented, and conventional CMAC's online learning speed and its accuracy are improved at the same time.
采用基于信任分配的CMAC神经网络实现了该算法，显著提高了传统CMAC在线学习的速度与准确性。
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。
The experimental results show that this approach can speed up the learning of BP neural network effectively.
理论分析和实验结果均表明，该方法可以有效地缩短BP网络的学习时间。
The intrinsic defects of artificial neural network, e. g. , its slow learning speed. existence of partial minimum points, are solved.
有效地克服了人工神经网络学习速度慢、存在局部极小点的固有缺陷。
Finally, the benchmark of function simulation shows that the precision and size of network are as the same as GAP-RBF, but the learning speed modified GAP-RBF is improved.
最后，函数模拟实验表明，所提出的算法在保留了原gap - RBF算法较高的精确度与紧凑的网络规模的基础上，提高了GAP - R BF对单个样本的学习速度。
This paper presents a model for identifying induction motor speed using the recurrent neural network, which is trained by a real time recurrent learning algorithm.
本文利用递归神经网络来建立异步电机转速辩识模型，其网络学习采用实时递归学习算法。
The results show that the neutral network controller has shelf-learning and self-adaptive functions, and has better control effect in speed tracking, compared with traditional PI controller.
仿真结果表明，相对于常规PI控制器，该神经网络控制器具有自学习，自适应功能，速度跟踪获得了满意的控制效果。
Experiments show that this algorithm can speed up the learning process of network, and solve the problem of local extremum in learning process to a certain extend.
实验表明，该算法不仅能明显提高网络的学习速度，而且可较好地避免学习过程陷入局部极小点而导致学习失败。
The structure of multi-layer feedback forward neural network is optimized by improved PSO. Learning quality and training speed of the neural network are improved.
提出的自适应粒子群优化算法，用于优化多层前馈神经网络的拓扑结构，提高了神经网络的学习质量和速度。
Our previous work has shown that the network was effective in improving two difficulties, a convergence to local minimal and a slow learning speed.
并对以前神经网络中的两个难点：局部极小和收敛速度慢的问题进行分析。
The modified neural network's learning speed is much increased because of the linear network and the recursive least square.
由于线性网络的引入及递推最小二乘法的使用，大大提高了网络的学习速度。
Based on the self-learning property of neural network, an adaptive control method for speed ring of a gyroscope-stabilized platform is put forward in the paper.
提出一种利用神经网络的自学习特性，对陀螺稳定平台的速度环进行自适应控制的方法。
The neural network predictive controller was used to control the cement flux, its simple network structure and rapid learning speed can be applied to the project realization.
水泥流量采用神经元预测控制，该算法网络结构简单、收敛速度快，现场使用效果良好。
In this paper, we introduce one high speed IP network based, inter-cities multimedia distance learning sys-tem.
文章介绍一个基于高速IP网络的跨城市的多媒体远程教育系统。
During the process of learning the RBF neural network, one can accelerate the converging process of learning by regulating the learning speed according to a performance function.
在RBF神经网络的学习过程中，根据性能函数调节学习率，可以加快学习的收敛过程。
After thoroughly describing learning and training of the neuro network of the high-speed high precision robot, this paper analyses four veriant…
所介绍的方法为高速高精度机器人的实时控制提供了一种有效的途径。
After thoroughly describing learning and training of the neuro network of the high-speed high precision robot, this paper analyses four veriant…
所介绍的方法为高速高精度机器人的实时控制提供了一种有效的途径。
应用推荐