Exponential H∞ Weight Learning of Takagi–Sugeno Fuzzy Neutral-Type Neural Networks with Reaction–Diffusion

The exponential H ∞ stabilization of Takagi–Sugeno fuzzy neutral-type neural networks with reaction–diffusion is investigated. A simple condition taking the form of linear matrix inequalities is presented by using Lyapunov functional, slack matrices, and the loop-invariant property of matrix trace. With the feasible solutions to these inequalities, a weight learning rule is derived to guarantee exponential H ∞ stability of the considered neural network. Then, a new LMIs-based condition on the existence of the weight learning rule is obtained by employing a more complex Lyapunov functional and the Jensen integral inequality. Finally, two numerical examples are given to illustrate the validity and lower conservatism of the proposed results.