l2-l∞ Filtering for Discrete Time-Delay Markovian Jump Neural Networks

This paper considers the l(2)-l(infinity) filter problem for discrete time-delay Markovian jump neural networks. Attention is focused on the design of a reduced-order filter to guarantee stochastic stability and a prescribed l(2)-l(infinity) performance for the filtering error system. In terms of linear matrix inequalities (LMIs), a delay-dependent sufficient condition for the solvability of the addressed problem is presented. When these LMIs are feasible, an explicit expression for the desired reduced-order filter is given. A numerical example is provided to show the effectiveness of the proposed results.