Search

Your search keyword '"Zhigang Zeng"' showing total 4 results
Start Over Author "Zhigang Zeng" Topic stability
4 results on '"Zhigang Zeng"'

1. Pattern memory analysis based on stability theory of cellular neural networks

Author

De-Shuang Huang, Zhigang Zeng, and Zengfu Wang

Subjects
Artificial neural network, Computer science, Applied Mathematics, Stability (learning theory), Cellular neural networks, Isolated equilibrium point, Perceptron, Domain (software engineering), Modelling and Simulation, Modeling and Simulation, Stability theory, Cellular neural network, Convergence (routing), Memory analysis, Stability, Algorithm, Pattern memory
Abstract

In this paper, several sufficient conditions are obtained to guarantee that the n-dimensional cellular neural network can have even (⩽2n) memory patterns. In addition, the estimations of attractive domain of such stable memory patterns are obtained. These conditions, which can be directly derived from the parameters of the neural networks, are easily verified. A new design procedure for cellular neural networks is developed based on stability theory (rather than the well-known perceptron training algorithm), and the convergence in the new design procedure is guaranteed by the obtained local stability theorems. Finally, the validity and performance of the obtained results are illustrated by two examples.

Published
2008

2. Improved Conditions for Global Exponential Stability of Recurrent Neural Networks With Time-Varying Delays.

Author

Zhigang Zeng and Wang, Jun

Subjects
*ARTIFICIAL neural networks, *TIME delay systems, *EXPONENTIAL functions, *STABILITY (Mechanics), *GEOMETRIC connections
Abstract

This paper presents new theoretical results on global exponential stability of recurrent neural networks with bounded activation functions and time-varying delays. The stability conditions depend on external inputs, connection weights, and time delays of recurrent neural networks. Using these results, the global exponential stability of recurrent neural networks can be derived, and the estimated location of the equilibrium point can be obtained. As typical representatives, the Hopfield neural network (HNN) and the cellular neural network (CNN) are examined in detail. [ABSTRACT FROM AUTHOR]

Published
2006
Full Text
View/download PDF

3. Stability Analysis of Delayed Cellular Neural Networks Described Using Cloning Templates.

Author

Zhigang Zeng, Jun Wang, and Xiaoxin Liao

Subjects
*ARTIFICIAL neural networks, *ARTIFICIAL intelligence, *DIGITAL computer simulation, *ELECTRONIC circuits, *DIGITAL electronics, *ELECTRONIC systems
Abstract

In this paper, we show that any N × M-dimensional delayed cellular neural network described using cloning templates can have no more than 3N×M isolated equilibrium points and 2 N×M of these equilibrium points located in saturation regions are locally exponentially stable. In addition, we give the conditions for the equilibrium points to be locally exponentially stable when the equilibrium points locate the designated saturation region. These conditions improve and extend the existing stability results in the literature. The conditions are also very easy to be verified and can be checked by direct examination of the templates, regardless of the number of cells. Finally, the validity and performance of the results are illustrated by use of two numerical examples. [ABSTRACT FROM AUTHOR]

Published
2004
Full Text
View/download PDF

4. A domain attraction criterion for interval fuzzy neural networks

Author

Chuandong Li, Tingwen Huang, and Zhigang Zeng

Subjects
Equilibrium point, Adaptive neuro fuzzy inference system, Mathematical optimization, Neuro-fuzzy, Interval (mathematics), Interval fuzzy neural networks, Stability (probability), Domain (mathematical analysis), Computational Mathematics, Computational Theory and Mathematics, Exponential stability, Modelling and Simulation, Modeling and Simulation, Fuzzy number, Domain attraction, Stability, Mathematics
Abstract

In this paper, we study qualitative properties of equilibrium points in a class of interval fuzzy neural networks, and obtain an estimate on the domain of robust attraction of locally exponentially stable equilibrium points. Both the conditions and the estimate are formulated in terms of the parameter intervals, so they are easily verifiable. The result can be used for the evaluation of fault-tolerance capability for interval fuzzy neural networks.

Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results