State Estimation for a Class of Discrete-Time BAM Neural Networks With Multiple Time-Varying Delays

For a class of discrete-time bidirectional associative memory neural networks (DTBAMNNs) with multiple time-varying delays, the issue state estimation is studied. By propose mathematical induction method, we first investigate novel delay-dependent and -independent global exponential stability (GES) criteria error system. The obtained GES are described by linear scalar inequalities. Then, observer derived via theory generalized matrix inverses. These conditions very simple, which convenient to verify based on standard software tools (for example, YALMIP). Finally, present two illustrative examples effectiveness theoretical results.