查询词典 neural network

Based on Spall,the Neural Network that concealed level can automatically increase is adopted to control the Neural Network structure and it can realize optimization control of unfounded nonlinear random system.

因为系统模型未知，本文在Spall［1］的基础上采用了隐层能自动增加的神经网络，通过实时的对神经网络的结构进行控制，可以实现对未建模型的非线性随机系统的最优控制。

The templet generating for HOQ based on CBR and Artificial Neural Network is also proposed with emphasis on profound analysis of the generalization ability of the learned neural network.

提出了以基于事例推理和人工神经网络为核心的质量屋模板生成技术，着重对学习后神经网络的泛化能力进行了深入分析。

A chaos optimum and neural network calculation model was built based on plenty of testing data of concrete intensity to cover the shortage of single BP neural network, such as slow astringency and easy torpidity.

摘要依据混凝土标准试块强度检测数据，建立了混沌优化的神经网络计算模型，从而克服传统BP网络收敛速度慢、易出现麻痹现象等不足。

A chaos optimum and neural network calculation model was built based on plenty of testing data of concrete intensity to cover the shortage of single BP neural network , such as slow astringency and easy torpidity .

依据混凝土标准试块强度检测数据，建立了混沌优化的神经网络计算模型，从而克服传统BP网络收敛速度慢，易出现麻痹现象等不足。

A new hybrid learning algorithm is proposed to train the fuzzy neural network based on TSK fuzzy model. Firstly, fuzzy c-means algorithm is applied to initialize the parameters of the fuzzy neural network.

最后用该建模方法建立了聚合反应中熔融指数的软测量模型，并与完全基于梯度下降的模糊神经网络软测量模型进行比较。

A neural-network-based robust compensating control method is proposed for the robots with constructed and unconstructed uncertainty The robust controller consists of a computed torque controller and add-on compensating controller The effective way using neural network to estimate the system uncertainty is also given.

四、对具有结构型和非结构型不确定性的机器人提出了一种基于神经网络补偿的鲁棒控制方法，控制器由一个计算力矩控制器和一个可切入的神经网络补偿控制器组成，给出一种利用神经网络学习机器人不确定性的有效途径。

The design of a FIR linear phase filter based onBP neural network algorithm is introduced, get the unit impulse response of the filter by training the wieght of the BP neural network.

摘 要：本文将BP神经网络算法应用于FIR线性相位数字滤波器的设计中，通过训练神经网络的权值，得到滤波器的单位冲激响应。

There are some disadvantages in BP algorithm, such as low rate of convergence, easily falling into local minimum point and weak global search capability. In order to settle these problems, a genetic algorithm was used to train BP neural network to replace classical learning algorithms. An evolutionary neural network learning algorithm was founded.

针对BP算法存在收敛速度慢、容易陷入局部极小值及全局搜索能力弱等缺陷，采用遗传算法训练BP神经网络，取代了一些传统的学习算法，设计了基于进化神经网络的学习算法。

BP neural network based on adaptive UKF is introduced in this paper for the standard BP neural network has slow converges, local minimum value and weak generalization ability.

针对BP神经网络收敛速度慢、容易陷入局部极小值点和泛化能力差等问题，基于自适应Kalman滤波理论，提出一种自适应非线性滤波训练BP神经网络的方法。

BP neural network based on adaptive UKF is introduced in this paper for the standard BP neural network has slow converges,local minimum value and weak generalization ability.It can train weight of BP and improve the efficiency of BP without linearization by using the frame of Kalman filters and adaptive factor to adjust the variance of dynamic model.

1引言1986年，Rum elhart和M cC lelland等人在多层前向神经网络模型的基础上，提出了误差反向传播学习算法(BackPropagation简写BP)，该算法是目前在神经网络中应用最广泛的算法，它解决了多层前向神经网络的学习问题[1]。

The split between the two groups can hardly be papered over.

这两个团体间的分歧难以掩饰。

This approach not only encourages a greater number of responses, but minimizes the likelihood of stale groupthink.

这种做法不仅鼓励了更多的反应，而且减少跟风的可能性。