Article ID Journal Published Year Pages File Type
411789 Neurocomputing 2015 6 Pages PDF
Abstract

This paper focuses on the problem of delay-dependent dissipativity analysis for a class of neural networks with time-varying delays. A free-matrix-based inequality method is developed by introducing a set of slack variables, which can be optimized via existing convex optimization algorithms. Then, by employing Lyapunov functional approach, sufficient conditions are derived to guarantee that the considered neural networks are strictly (Q,S,R)(Q,S,R)-γ-dissipative. The conditions are presented in terms of linear matrix inequalities and can be readily checked and solved. Numerical examples are finally provided to demonstrate the effectiveness and advantages of the proposed new design techniques.

Related Topics
Physical Sciences and Engineering Computer Science Artificial Intelligence
Authors
, , , , ,