Exponential Stability of Delayed Hopfield Neural Networks by Using Comparison Method
The exponential stability of delayed Hopfield neural networks is studied by comparison principle. Hopfield neural networks can be regarded as a linear system perturbed by the exterior input. Based on this view of point, the method of variation of coefficient is used to solve the system’s solutions, which are estimated by its comparison system. By this comparison system, which is a linear differential difference equation, and by using theory of linear functional differential equation, some stability criteria are obtained, which is very simple to verified. An examples are given to show the efficiency of the results in this paper.
KeywordsNeural Network Exponential Stability Comparison System Comparison Principle Negative Real Part
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Hopfield, J.J.: Neural Networks and Physical Systems with Emergent Collective Computational Abilities. Proc. Natl. Acad. Sci. USA, 79 (1982) 2554–2558PubMedCrossRefGoogle Scholar
Hopfield, J.J.: Neurons with Graded Response have Collective Computational Properties Like Those of Two-state Neurons. Proc. Natl. Acad. Sci. USA, 81 (1984) 3088–3092PubMedCrossRefGoogle Scholar
Liao, W., Liao, X.: Robust Stability of Time-Delayed Interval CNN in Noisy Environment. Acta Automat Sin, 30(2)(2004) 300–305Google Scholar
Zeng, Z., Wang, J., Liao, X.: Global Asymptotic Stability and Global Exponential Stability of Neural Networks with Unbounded Time-varying Delays. IEEE Trans. Circuits Systs, 52 (2005) 168–173CrossRefGoogle Scholar
Shen, Y., Liao, X.: Exponential Stability of Delayed Hopfield Neural Networks. Acta Mathematica Sci, 19 (1999) 211–218Google Scholar
Zeng, Z. , Wang, J., Liao, X.: Global exponential stability of neural networks with time-varying delays. IEEE Trans. Circuits Sys: 50 (2003) 1353–1358CrossRefGoogle Scholar
Liao, X.: Studies on Mathematic Meaning of Phisic Parameters in Hopfield Neural Networks. Science in China (Series E), 33 (2003) 127–136CrossRefGoogle Scholar
© Springer-Verlag Berlin Heidelberg 2008