研究了离散时间神经网络的全局指数稳定性问题。
In this paper, the global exponential stability of discrete-time neural networks is discussed.
针对多变量非线性离散时间系统设计多模型神经网络解耦控制器。
A multiple models neural network decoupling controller is designed to control the multivariable nonlinear discrete time system.
本文主要针对离散时间动力系统的动力学性质研究，包括差分方程及离散人工神经网络两个方面的研究。
This dissertation aims at the study of dynamical properties of discrete-time dynamical systems, which include difference equations and discrete neural networks.
研究了一类带有离散和分布时间滞后的不确定时滞细胞神经网络(DCNN)的全局渐进稳定性。
The global asymptotic stability for a class of uncertain delayed cellular neural networks (DCNN) with discrete and distributed time-varying delays is studied in this paper.
讨论了利用仅含一个隐层的前馈多层神经网络来辨识离散时间非线性动态系统时的模型检验问题。
This paper investigates the problem of the model validation in identifying discrete-time-nonlinear dynamic systems by using neural networks with a single hidden layer.
针对一类不确定的离散时间非线性非最小相位动态系统，提出了一种基于神经网络和多模型的直接自适应控制方法。
A direct adaptive control approach is proposed for a class of uncertain discrete time nonlinear non-minimum phase dynamical systems.
第三章对变系数离散时间混合时滞细胞神经网络模型周期解的存在性与全局指数稳定性进行了讨论。
In Chapter 3, we discuss the existence and global exponential stability of periodic solutions for discrete-time cellular neural network with mixed delays and variable coefficients.
最后，利用人工神经网络原理，对其支护参数进行了研究，并提出了利用离散元来确定二次支护时间的方法。
Lastly, timbering parameter is studied by utilizing Artificial NeuralNetwork (ANN), and put forward using Discrete Element Method (DEM) to confirm 2nd support time.
最后，利用人工神经网络原理，对其支护参数进行了研究，并提出了利用离散元来确定二次支护时间的方法。
Lastly, timbering parameter is studied by utilizing Artificial NeuralNetwork (ANN), and put forward using Discrete Element Method (DEM) to confirm 2nd support time.
应用推荐