立方形递归网络是一类具有良好拓扑性质的互连网络模型。
Cubelike recursive networks are novel sorts of interconnection networks that have some attractive topological properties and good parameters.
指出递归网络要实现逼近，需考虑初始条件、嵌入维数、逼近时效等因素。
And point out that in order to realize the approximation of recurrent networks, the initial conditions, embed dimension and approximation effects must be considered.
该网络控制器的隐含层由带有输出反馈和激活反馈的混合局部连接递归网络组成。
It is composed of a hybrid locally connected recurrent network with an activation feedback and an output feedback respectively in the hidden layer.
本文基于一个全连接递归网络结构，给出一种新的信息理论的盲源信号分离准则。
A new information theory criterion for blind source separation based on a recurrent neural network is proposed.
提出一种对水轮发电机组水压频率进行综合调节的记忆递归网络灵敏度预测控制器。
A sensitivity predictive controller with memory recurrent network for use in the comprehensive control of the water hammer and the frequency is proposed.
辨识结果表明，动态递归网络模型优于传统辨识模型，适于非线性、不确定结构的辨识。
Results of identification show that the Elman's recurrent model is superior to the traditional model. It is adaptive to the identification of the non linear and uncertain structure.
通过仿真，与前馈时延网络与对角递归网络的比较研究，说明了在实时故障诊断系统中输出递归网络结构的优越性。
Comparing with time delayed feedforward network and diagonal recurrent network, output recurrent network shows its advantages in real-time fault detection system.
本文介绍了动态对角递归网络，并针对BP算法收敛慢的缺点，将递推预报误差学习算法应用到神经网络权值和域值的训练。
To overcome the slow convergence of the BP algorithm, recursive prediction error algorithm is proposed, which can train both the weight and the bias.
提出一种准对角递归神经网络(QDRNN)结构及学习算法。
A structure and training algorithm for quasi-diagonal recurrent neural network (QDRNN) is presented.
本文对一种规则的栅格状网络进行了理论分析，并分别针对两种路由准则，采用递归方法推导出了评价网络性能的计算公式。
This paper analyses a regular grid network for two kinds of routing standard theoretically, and derives recursive formular to find the network performance.
模拟实验结果表明，递归反向传播控制神经网络对多种形式的超声马达参考速度都有很好的控制效果。
Numerical results show that the recurrent back propagation control neural network controller has good effectiveness for various kinds of reference speeds of the ultrasonic motor.
由于其反馈特征，使得递归神经网络模型能获取系统的动态响应特性。
With the feedback behavior, the recurrent neural network can catch up with the dynamic response of the system.
这是我写的关于对角递归神经网络的程序，或许对你有所帮助。
This is written about me on the diagonal recurrent neural network procedures, may be helpful to you.
实验结果表明，递归神经网络用于飞机目标识别是有效可行的。
The result demonstrates the feasibility of using recurrent neural networks for aircraft target recognition.
这为快速训练复值递归神经网络提供了一条新的途径。
This provides a new way to the fast training of complex valued recurrent neural network.
提出一种在用户-网络接口处利用对角递归神经网络(DRNN)作为自适应预测器，实现AT M网络自适应拥塞控制的模型。
This paper presents an adaptive congestion control model in ATM networks at the user to network interface by using a diagonal recurrent neural network (DRNN) as an predictor.
研究了一类随机变时滞递归神经网络的几乎指数稳定性问题。
The almost surely exponential stability of stochastic recurrent neural networks with time-varying delays is investigated.
为了考察该系统的动态性能，采用递归BP神经网络对该系统进行辨识。
To test the dynamic property, this pneumatic fatigue test system was identified by a recursive BP neural network.
基于递归神经网络给出了仅含一个非线性环节的一类非线性系统的自适应控制方案。
A scheme of adaptive control based on recurrent neural network is presented for a class of nonlinear systems only with a nonlinear part.
无限区间上s -分布时滞广义递归神经网络模型概周期解的全局渐近稳定性。
Global asymptotic stability of general recurrent neural network models with S-type distributed delays on infinite intervals.
提出了一种基于对角递归神经网络的盲均衡算法。
A new blind equalization algorithm based on diagonal recurrent neural networks (DRNN) is proposed.
分析了动态递归神经网络系统辨识的参数学习算法。
The parameter learning algorithm of dynamic recurrent neural network based on system identification is analyzed. D.
与改进BP算法相结合，各取所长，形成集成化动态递归神经网络建模辨识算法。
The identification algorithm integrating the forward evolutionary algorithm and improved BP algorithm for the dynamic recursive neural network model is formed.
研究了带时变时滞的递归神经网络的全局渐近稳定性。
The problem of the globally asymptotical stability of recurrent neural networks with time varying delay is investigated.
接着，结合其存在的问题，对动态递归神经网络、R BF神经网络和自适应逆控制进行了算法研究。
Then, aiming at the existing problem, the algorithm of dynamic recurrent neural network, RBF neural network and adaptive inverse control is studied in the paper.
针对仿射非线性系统，提出了一种新型的基于动态递归模糊神经网络(DRFNN)的间接自适应控制器。
A novel indirect adaptive controller based on dynamic recurrent fuzzy neural network (DRFNN) is proposed for affine nonlinear system.
针对静态网络无法处理暂态问题，对具有递归环节的动态模糊神经网络进行了研究。
Since a static fuzzy neural network cannot deal with the temporal problem, a dynamic fuzzy neural network (DFNN) with recurrent units is proposed.
本文用递归神经网络逼近非线性ARMA模型预测电力短期负荷。
The recursive neural network based nonlinear approaching ARMA model is adopted for short-term power load prediction in this paper.
对RPE算法进行了改进和补充，使之适用于简单递归网，用来对网络的权值和阈值进行调整。
This RPE algorithm was adapted to the simple recurrent network by making improvement and complementarity, and the weight and the threshold of the network can be adjusted at the same time.
对RPE算法进行了改进和补充，使之适用于简单递归网，用来对网络的权值和阈值进行调整。
This RPE algorithm was adapted to the simple recurrent network by making improvement and complementarity, and the weight and the threshold of the network can be adjusted at the same time.
应用推荐