The state estimation problem is discussed for discrete Markovian jump
neural networks with time-varying delays in terms of linear matrix inequality
(LMI) approach. The considered transition probabilities are assumed to
be time-variant and partially unknown. The aim of the state estimation
problem is to design a state estimator to estimate the neuron states and
ensure the stochastic stability of the error-state system. A delay-dependent
sufficient condition for the existence of the desired state estimator is proposed.
An explicit expression of the desired estimator is also given. A numerical
example is introduced to show the effectiveness of the given result.