Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence
Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence
Global attractivity in delayed Hopfield neural network models
SIAM Journal on Applied Mathematics
Dynamics of a class of discete-time neural networks and their comtinuous-time counterparts
Mathematics and Computers in Simulation
Neural Networks for Optimization and Signal Processing
Neural Networks for Optimization and Signal Processing
New results for robust stability of dynamical neural networks with discrete time delays
Expert Systems with Applications: An International Journal
Improved asymptotic stability criteria for neural networks with interval time-varying delay
Expert Systems with Applications: An International Journal
WSEAS Transactions on Mathematics
Expert Systems with Applications: An International Journal
Mathematics and Computers in Simulation
| Hi-index | 12.06 |
In the current paper, a class of general neural networks with time-varying coefficients, reaction-diffusion terms, and general time delays is studied. Several sufficient conditions guaranteeing its global exponential stability and the existence of periodic solutions are obtained through analytic methods such as Lyapunov functional and Poincare mapping. The obtained results assume no boundedness, monotonicity or differentiability of activation functions and can be applied within a broader range of neural networks. Among the presented conditions, some are independent of time delay and expressed in terms of system parameters, so easy to verify and of leading significance in applications. For illustration, an example is given.