Global Exponential Stability of Recurrent Neural Networks with Time-Varying Delay
A new theoretical result on the global exponential stability of recurrent neural networks with time-varying delay is presented. It should be noted that the activation functions of recurrent neural network do not require to be bounded. The presented criterion, which has the attractive feature of possessing the structure of linear matrix inequality, is a generalization and improvement over some previous criteria.
KeywordsLinear Matrix Inequality Global Stability Recurrent Neural Network Piecewise Linear Function Librium Point
Unable to display preview. Download preview PDF.