Mean Square Exponential Stability of Stochastic High-Order Hopfield Neural Networks with Time-Varying Delays

Xiang Dong Shi

doi:10.4028/www.scientific.net/AMM.303-306.1532

Paper Titles

Discrimination of Two-Mixture Fragrances Odor Using Artificial Odor Recognition System with Ensemble Backpropagation Neural Networks
p.1514

A Constrained Particle Swarm Optimization Algorithm with Oracle Penalty Method
p.1519

The Reasoning and Application Model for Topological Relations between a Concave Region and a Simple Broad Boundary Region
p.1524

A Model for Representation and Reasoning of Topological Relations between a Concave Region and a Simple Broad Boundary Region
p.1528

Mean Square Exponential Stability of Stochastic High-Order Hopfield Neural Networks with Time-Varying Delays
p.1532

An On-Line Adaptive Product Fusion Tracking Algorithm Based on Multiple-Cue
p.1536

BP Neural Network Research Based on Three Convergence Improved LM Algorithm
p.1543

GPU-Based Rendering Method of Virtual Human Motion
p.1547

A Simple Algorithm for Video Object Tracking
p.1552

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 303-306Mean Square Exponential Stability of Stochastic...

Mean Square Exponential Stability of Stochastic High-Order Hopfield Neural Networks with Time-Varying Delays

Abstract:

The paper considers the problems of global exponential stability for stochastic delayed high-order Hopfield neural networks with time-varying delays. By employing the linear matrix inequality(LMI) and the Lyapunov functional methods, we present some new criteria ensuring globally mean square exponential stability. The results impose constraint conditions on the network parameters of neural system independent. The results are applicable to all continuous non-monotonic neuron activation functions.

You might also be interested in these eBooks

Sensors, Measurement and Intelligent Materials

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 303-306)

Pages:

1532-1535

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.303-306.1532

Citation:

Cite this paper

Online since:

February 2013

Authors:

Xiang Dong Shi

Keywords:

High-Order Hopﬁeld Neural Networks, Linear Matrix Inequality (LMI), Lyapunov Functional, Mean Square Exponential Stability, Stochastic Delay, Time-Varying Delays

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] J. Hopﬁeld. Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Natl. Acad. Sci. U.S.A. Biophysics 81 (1984) 3088-3092.

DOI: 10.1073/pnas.81.10.3088

Google Scholar

[2] L. O. Chua, L. Yang. Cellular networks: theory. IEEE Trans. Syst. 35 (10) (1988) 1257- 1272.

Google Scholar

[3] L. Personnaz, I. Guyon, G. Dreyfus. High-order neural networks: information storage without errors. Euro Phys. Lett. 4 (8) (1987) 863-867.

DOI: 10.1209/0295-5075/4/8/001

Google Scholar

[4] D. Psaltis, C. H. Par, J. Hong. Higher-order associative memories and their optical implementations. Neural Networks 1 (2) (1988) 149-163.

DOI: 10.1016/0893-6080(88)90017-2

Google Scholar

[5] X.X. Liao, X. Mao, Exponential stability and instability of stochastic neural networks, Stochastic. Anal. Appl. 14(2) (1996a)165-185.

DOI: 10.1080/07362999608809432

Google Scholar

[6] Lin Wan, Jianhua Sun. Mean square wxponential stability of stochastic delayed Hopﬁeld neural networks. Physics Letters A 343 (2005) 306-318.

DOI: 10.1016/j.physleta.2005.06.024

Google Scholar