Improved stability criteria for uncertain delayed neural networks

This paper is concerned with the stability problem of uncertain delayed neural networks. The system possesses time-varying and norm-bounded uncertainties. An improved integral inequality lemma is proposed to handle the cross-product terms occurred in the derivative of Lyapunov functional. By using the new lemma and a novel delay decomposition approach, new robust stability criteria for time varying delay neural networks with structured linear fractional form uncertainties are proposed in terms of LMIs. The sufficient conditions obtained in this paper are less conservative than those in the former literature.