Robust Exponential Stability of Recurrent Neural Networks With Multiple Time-Varying Delays

A new result on global exponential robust stability of neural networks with time-varying delays

“…Note that the activation functions are unbounded, and the function of time delays are not differentiable, whereas the activation functions are assumed to be bounded in [20,21,23], and the time delays are assumed to be constants in [17,18,22] and differentiable in [24]. Then, the results derived in the above literatures are not available to this example.…”

Global robust stability of interval delayed neural networks: Modified approach

“…If W is a matrix, its norm W 2 is defined as W 2 = sup{ Wx : x = 1}= max (W T W), where max (W T W) denotes the maximum eigenvalue of W T W. The problem of global robust stability of Equation (1) with Equations (5)-(7) has generated considerable interest (for example, References [1][2][3][4][5][6][7][8][9][10][11][12][13]). In the present letter, a new criterion for the global robust stability of Equation (1) with Equations (5)- (7) is presented.…”

Improved Stability Results for Stochastic Cohen–Grossberg Neural Networks with Discrete and Distributed Delays

“…Thus, the stability analysis problem, as one of the most important problems for neural networks with time-delay, has been received considerable research attention. Many sufficient conditions (either delay-independent or delay-dependent) have been proposed to verify the asymptotical or exponential stability for neural networks with different types of time delay, such as discrete time-varying delay and distributed time delay, see, [5,9,10,12,16,18,[24][25][26][27][28][29]31,33,34] and the references therein. For Cohen-Grossberg neural networks with both time-varying and continuously distributed delays, by introducing some free-weighting matrices and utilizing the descriptor system approach, several delay-dependent stability conditions are obtained in [9], which are based on linear matrix inequalities (LMIs) technique.…”