Global asymptotic stability of recurrent neural networks with multiple time-varying delays [0.03%]
具有多个变时滞的递归神经网络的全局渐近稳定性
Huaguang Zhang,Zhanshan Wang,Derong Liu
Huaguang Zhang
In this paper, several sufficient conditions are established for the global asymptotic stability of recurrent neural networks with multiple time-varying delays. The Lyapunov-Krasovskii stability theory for functional differential equations ...
Stability and Hopf bifurcation of a general delayed recurrent neural network [0.03%]
具有一般时滞的递归神经网络的稳定性及Hopf分支
Wenwu Yu,Jinde Cao,Guanrong Chen
Wenwu Yu
In this paper, stability and bifurcation of a general recurrent neural network with multiple time delays is considered, where all the variables of the network can be regarded as bifurcation parameters. It is found that Hopf bifurcation occu...
Multilayer perceptrons: approximation order and necessary number of hidden units [0.03%]
多层感知器：逼近次序和隐藏单元的必要数量
Stephan Trenn
Stephan Trenn
This paper considers the approximation of sufficiently smooth multivariable functions with a multilayer perceptron (MLP). For a given approximation order, explicit formulas for the necessary number of hidden units and its distributions to t...
Robust neural network tracking controller using simultaneous perturbation stochastic approximation [0.03%]
基于同时扰动随机逼近的鲁棒神经网络跟踪控制律
Qing Song,James C Spall,Yeng Chai Soh et al.
Qing Song et al.
This paper considers the design of robust neural network tracking controllers for nonlinear systems. The neural network is used in the closed-loop system to estimate the nonlinear system function. We introduce the conic sector theory to est...
Min Qi,G Peter Zhang
Min Qi
Despite its great importance, there has been no general consensus on how to model the trends in time-series data. Compared to traditional approaches, neural networks (NNs) have shown some promise in time-series forecasting. This paper inves...
A galerkin/neural-network-based design of guaranteed cost control for nonlinear distributed parameter systems [0.03%]
基于加尔尔金/神经网络的非线性分布参数系统保性能控制设计方法研究
Huai-Ning Wu,Han-Xiong Li
Huai-Ning Wu
This paper presents a Galerkin/neural-network- based guaranteed cost control (GCC) design for a class of parabolic partial differential equation (PDE) systems with unknown nonlinearities. A parabolic PDE system typically involves a spatial ...
Equilibria and their bifurcations in a recurrent neural network involving iterates of a transcendental function [0.03%]
迭代超越函数循环神经网络的平衡点及其分支分析
Bo Gao,Weinian Zhang
Bo Gao
Some practical models contain so complicated mathematical expressions that it is hard to determine the number and distribution of all equilibria, not mentioning the qualitative properties and bifurcations of those equilibria. The three-node...
The greatest allowed relative error in weights and threshold of strict separating systems [0.03%]
严格分离系统中权重和阈值的最大容许相对误差
Josep Freixas,Xavier Molinero
Josep Freixas
An important consideration when applying neural networks is the sensitivity to weights and threshold in strict separating systems representing a linearly separable function. Perturbations may affect weights and threshold so that it is impor...
Pattern representation in feature extraction and classifier design: matrix versus vector [0.03%]
模式表示在特征提取与分类器设计中的研究：矩阵和向量
Zhe Wang,Songcan Chen,Jun Liu et al.
Zhe Wang et al.
The matrix, as an extended pattern representation to the vector, has proven to be effective in feature extraction. However, the subsequent classifier following the matrix-pattern- oriented feature extraction is generally still based on the ...
Fast-learning adaptive-subspace self-organizing map: an application to saliency-based invariant image feature construction [0.03%]
快速学习自适应子空间自组织特征地图的应用：基于显著性的不变图像特征构造方法研究
Huicheng Zheng,Grégoire Lefebvre,Christophe Laurent
Huicheng Zheng
The adaptive-subspace self-organizing map (ASSOM) is useful for invariant feature generation and visualization. However, the learning procedure of the ASSOM is slow. In this paper, two fast implementations of the ASSOM are proposed to boost...