New delay-dependent stability criteria for neutral-type neural networks with mixed random time-varying delays

作者：Shi, Kaibo^*; Zhong, Shouming; Zhu, Hong; Liu, Xinzhi; Zeng, Yong

来源：Neurocomputing, 2015, 168: 896-907.

DOI：10.1016/j.neucom.2015.05.035

• Neutral-type neural networks
• Stability analysis
• Terms-Quadratic convex combination
• Mixed random time-varying delays
• Linear matrix inequality

This study is concerned with the problem of stability analysis of neutral-type neural networks with mixed random time-varying delays. Firstly, by using a novel and resultful mathematical approach and considering the sufficient information of neuron activation functions, improved delay-dependent stability results are formulated in terms of linear matrix inequalities (LMIs). Secondly, in order to obtain less conservative delay-dependent stability criteria, an augmented novel Lyapunov-Krasovskii functional (LKF) that contains triple and quadruple-integral terms is constructed. Moreover, our derivation makes full use of the idea of second-order convex combination and the property of quadratic convex function, which plays a key role in reducing further the conservatism of conditions. Finally, four numerical examples are presented to illustrate the effectiveness and advantages of the theoretical results.

• 出版日期2015-11-30
• 单位电子科技大学