Improved Delay-dependent Stability for Neural Networks with Mixed Time-varying Delays

摘要：

　　This paper proposes improved delay-dependent stability criteria for neural networks with mixed time-varying delays as well as generalized activation functions.By constructing a novel Lyapunov functional and using Jensen inequality,improved stability criteria are derived to guarantee the globally asymptotic stability of the delayed neural networks.The criteria improve over some existing ones in that they have fewer matrix variables yet less conservatism,which is established theoretically.A numerical example is given to show the advantages of the proposed method in effectiveness and conservativeness.

关键词： Delay-dependent Neural networks Globally asymptotically stable Linear matrix inequality(LMI)

作者: Lei Zhang

作者单位: School of Information Science, Shanghai Ocean University, Shanghai, 201306

会议类型: 国际会议

会议名称: the 25th Chinese Control and Decision Conference(第25届中国控制与决策会议)

会议地点: 贵阳

会议语种:英文

页码: 2136-2141

在线出版日期: 2013-05-01（万方平台首次上网日期，不代表论文的发表时间）