Further Improvement on Delay-range-dependent Stability Criteria for Delayed Recurrent Neural Networks with Interval Time-varying Delays
- 5 Downloads
This paper considers the problem of delay-range-dependent stability analysis for a class of delayed recurrent neural networks (DRNNs) with a time-varying delay in a range. Based on the Lyapunov-Krasovskii functional and derive the time derivative of this with integral inequality approach (IIA), new delay-dependent stability criteria for the system are established in terms of linear matrix inequalities (LMIs), which can be solved easily by various efficient convex optimization algorithms. Information about the lower bound of the delay is fully used in the Lyapunov functional. Two examples are given to illustrate the effectiveness and the reduced conservatism of the proposed results.
KeywordsIntegral inequality approach (IIA) interval time-varying delay linear matrix inequality (LMI) recurrent neural network
Unable to display preview. Download preview PDF.
- S. Xu, J. Lam, D. W. C. Ho, and Y. Zhou, “A new LMI condition for delayed dependent asymptotic stability of delayed Hopfied neural networks,” IEEE Transactions on Circuits and Systems II-Express Briefs, vol. 52, pp. 230–234, 2006.Google Scholar
- L. B. Almeida, Back Propagation in Perceptrons with Feedback, in Neural Computers, ed. by R. Eckmiller, C. Von der Malsburg, Springer, New York, 1998.Google Scholar