State estimation for quaternion-valued neural networks with neutral delay

This essay focuses on the state estimation for quaternion-valued neural networks(QVNNs) with neutral delay. Some concise and natural conditions are established with quaternion direct method, and the estimator gain matrix $K$ can be acquired via solving a quaternion-valued LMI. Moreover, the delay-partitioning approach is adopted to obtain less conservation results. Finally, simulation results are demonstrated to check the correctness of theoretical results.