本文研究了连续神经网络在学习过程中结构摄动情况下网络的动态特性。
In this paper, the dynamic behaviors of continuous neural networks under structural variations in learning process are studied.
应用连续神经网络来解高频率离散问题，并采用最佳机票超额预定作为具体应用实例。
The paper aims at finding an alternation to apply the hopfield continuous network in the high rate discrete problems, which take an optimal overbooking scheme of airline as example.
那么，神经组织，只能是由连续的神经网络而不是分离的细胞组成的。
Nervous tissue must, then, be composed of a continuous network rather that discrete units.
Dieters不能看到具有“不能测量的纤细”的树突分支，而且，像许多其他人一样，从他的观察中，能够得出神经元在末端处融合在一起，从而构成一个连续的神经网络。
Dieters could not see the "immeasurably thin" terminal branches of the dendrites and, like many others, inferred from his observations that they must fuse to form a continuous network.
摘要研究了具反应扩散有限连续分布细胞神经网络的平衡点的存在性及全局指数稳定性问题。
The existence of the equilibrium point and global exponential stability of distributed delays neural networks with reaction-diffusion terms are investigated in this paper.
因此尝试采用模糊神经网络控制技术来进一步提高铜连续挤压生产的自动控制水平。
So we attempt to improve furtherly auto-control level of copper continuous extrusion production by fuzzy neural network control technology.
针对拉萨市道路交通噪声污染问题，运用人工神经网络理论和方法对拉萨市道路交通噪声的等效连续声级进行预测。
Aiming at the traffic noise problem of Lhasa, the author USES artificial neural network theory and method to predict the equivalent consecutive sound level of traffic noise in Lhasa.
细胞神经网络由于其连续时间的特性，因此在图象处理和图形辩识方面有着潜在的应用。
Cellula Neural Network has potential applications in image processing and recognizing because of its property of continuous time.
本文研究了一类具偏李·普希兹连续和单调增加激活函数的神经网络绝对指数稳定性问题。
This paper investigates the absolute exponential stability of generalized neural networks with a general class of partially Lipschitz continuous and monotone increasing activation functions.
针对信息科学和控制理论中经常涉及的一类泛函极值问题，提出基于连续回归神经网络的求解方法。
In this paper, the continuous time recurrent neural network is proposed to solve the functional minimization problem, which is often involved in estimation and control.
研究了一类具有连续分布延时的反馈神经网络模型的周期解的存在性和全局稳定性。
Both the global exponential stability and the existence of periodic solutions for a class of recurrent neural networks with continuously distributed delays (RNNs) are studied.
介绍了以连续合格品数为控制对象的方法以及实现该方法的神经网络核心技术。
The method of taking continuous qualified product counts as the control objects and the kernel technology of neural network for realizing this method are introduced.
因此尝试采用BP神经网络控制技术来进一步提高铜连续挤压生产的自动控制水平。
So we have attempted to apply the BP Neural Network Technology to improve further the automatic-control ability of the continuous extrusion process of copper.
构造一个三层BP神经网络，实现了连续函数的逼近。
This paper introduced a three layer BP neural network, and realized the approximation of a continuous function.
以最佳多项式逼近为度量，用构造性方法估计单隐层神经网络逼近连续函数的速度。
With the best polynomial approximation as a metric, the rate of approximation of the neural networks with single hidden layer to a continuous function is estimated by using a constructive approach.
前馈神经网络由于具有理论上逼近任意非线性连续映射的能力，因而非常适合于非线性系统建模及构成自适应控制。
Because the feedforward neural network has an ability of approach to arbitrary nonlinear mapping, it can be used effectively in the modeling and controlling of nonlinear system.
研究结果表明，基于动力模型的BP神经网络移动荷载识别方法，能够有效识别简支梁桥与连续梁桥上的移动车载；
The results show that the method of BP neural network used to identify moving force based on the dynamic model can effectively identify the moving force on the simple beams and continuous beams.
针对用户以任意字词连续哼唱的情况下，哼唱特征提取中音符分割、音符识别难度大的问题，提出了一种基于两级神经网络的哼唱特征提取方法。
A two-layer neural network for humming feature extraction is proposed for note segmentation and note recognition, when users sing consecutively with arbitrary words.
研究了模糊推理神经网络计算模型及其连续函数逼近能力。
This paper deals with the computational model for fuzzy reasoning neural network and its function approximation capability.
在二值输入情况下，尽管每个专家神经网络的输入特征数很小，对连续特征问题的学习结果仍是难以解释的。
With the assumption that the inputs are all binary numbers, the interpretation of an NNT trained on continuous features may be too complex to implement.
针对强化学习在连续状态和动作空间的泛化问题，人工神经网络是一种有效的解决方法。
And artificial neural network is a valid method to solve the generalization problem for the continuous state and action pairs in the reinforcement learning method.
根据这个理论，可知稀疏或部分连接的高阶神经网络象全连接的网络一样能够逼近任意连续函数。
According to this theory, we know that partially connected higher-order neural networks can approximate any continuous functions as fully connected neural networks can do.
通过数字复合正交神经网络的连续化算法处理获得了一种模拟复合正交神经网络，并作为前馈控制器。
The analog compound orthogonal neural network was obtained by means of a continuous algorithm treatment for a digital compound orthogonal neural network, and was used as the feedforward controller.
试验结果表明，加入聚类分析的径向基神经网络模型提高了连续预测的趋势准确率，降低了时间代价，并减小了模型的复杂度。
The result of this experiment shows that the modified RBF neuro-network increases trend accuracy in sequential predicting, while debasing the cost of time and reducing the complexity of the model.
基于滑动轴承油膜力数据库的连续性分析，建立了椭圆轴承非线性油膜力的神经网络计算模型。
Based on continuity analysis of oilfilm force databases of hydrodynamic bearings, neural network model of nonlinear oilfilm forces of elliptical bearings is developed.
本文采用一种新型的三层神经网络，即隐蔽层具有知识神经元的神经网络(NNKBN)模拟带状线电路中的十字交越不连续性。
A novel three-layer neural network with knowledge-based neurons (NNKBN) in hidden layer has been applied to model the crossover discontinuities in stripline circuits.
本文采用多层感知器建立了微带不连续性的神经网络模型。
The multi-layer perceptron is introduced to charcacterize the microstrip discontinuity by describings-parameters.
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。
RBF neural network is a kind of local approximation neural networks. In theory, it can approximate any continuous function if there is enough neuron.
还指出由于当前的连续小波神经网络主要使用传统BP神经网络的随机初始化方法和基于梯度的训练算法，因此存在收敛性差的缺点。
It is also indicated that current WNN has a poor convergence performance because of adopting the random initialization method and gradient training algorithm of traditional BP NET.
因此神经网络是一种具有高度非线性的超大规模连续时间动力学系统。
So artificial neural network is a dynamic system with highly non-lineal continued time.
应用推荐