Global Stability Analysis Of BAM Neural Networks And Discrete-Time Delayed Complex-Valued Neural Networks

In this paper,the research status and research methods of bidirectional associative memory(BAM)neural network and complex-valued neural network are analyzed and discussed.By using Homeomorphism theory,Lyapunov functional and some new inequality techniques,a novel LMI-based sufficient condition on global exponential stability of equilibrium point for neutral delayed BAM neural networks with delays in leakage terms and global asymptotic stability of equilibrium point for discrete-time delayed complex-valued neural networks is established.Unlike the existing paper,in our result,the existence and global exponential stability of equilibrium point for BAM neural network is dependent of time delay and the LMI condition for the existence of equilibrium point is identical to that for global stability of equilibrium point for the two classes neural network.on the other hand,in the discussion of the complex-valued neural network,the new complex matrix inequality is used to replace the matrix inequality in the existing literature.Hence,our results on global stability are less conservative,more novel than those in existing papers and are complementary to the previous known results.Four numerical simulations are performed to verify the effectiveness of our results.