Exponential estimates and exponential stability for neutral-type neural networks with multiple delays Academic Article

abstract

• 2014 Elsevier B.V. In this paper, exponential estimates and sufficient criteria for the exponential stability of neutral-type neural networks with multiple delays are given. First, because of the key role of the difference equation part of the neutral-type neural networks with multiple delays, some novel results concerning exponential estimates for non-homogeneous difference equations evolving in continuous time are derived. Then, by constructing several different Lyapunov-Krasovskii functionals combined with a descriptor transformation approach at some cases, several novel global and exponential stability conditions are presented and expressed in terms of linear matrix inequalities (LMIs), and the obtained results are less conservative and restrictive than the known results. Some numerical examples are also given to show their effectiveness and advantages over others.

authors

• Huang, Tingwen

published proceedings

• NEUROCOMPUTING

author list (cited authors)

• Liao, X., Liu, Y., Wang, H., & Huang, T.

citation count

• 23

complete list of authors

• Liao, Xiaofeng||Liu, Yilu||Wang, Huiwei||Huang, Tingwen

publication date

• February 2015

publisher

• Elsevier  Publisher

published in

• Neurocomputing  Journal

keywords

• Descriptor Transformation
• Exponential Estimate
• Exponential Stability
• Linear Matrix Inequalities
• Lyapunov-krasovskii Functional
• Neutral-type Neural Networks

Digital Object Identifier (DOI)

• 10.1016/j.neucom.2014.07.048

start page

• 868

end page

• 883

volume

• 149

issue

• PB

URL

• http%3A%2F%2Fdx.doi.org%2F10.1016%2Fj.neucom.2014.07.048