Novel robust stability criteria of neutral-type bidirectional associative memory neural networks
The existence, uniqueness and global robust exponential stability is analyzed for a class of uncertain neutral-type bidirectional associative memory (BAM) neural networks with time-varying delays. Without assuming the boundedness of the activation functions, by constructing a novel class of augmented Lyapunov-Krasovskii functional, new relaxed delay-dependent stability criteria of the unique equilibrium point are presented in terms of linear matrix inequalities (LMIs). Following the idea of convex combination and free-weighting matrices method, less conser-vative results are obtained. Two examples are given to illustrate the effectiveness of our proposed conditions.
Keywords: Global robust exponential stability, globally exponential stability, linear matrix inequality(LMI), neutral-type, bidirectional associative memory (BAM) neural network
Download Full-Text
ABOUT THE AUTHORS
Shu-Lian Zhang
Dalian Jiaotong University
Yu-Li Zhang
Dalian Jiaotong University
Shu-Lian Zhang
Dalian Jiaotong University
Yu-Li Zhang
Dalian Jiaotong University
