Bidirectional associative memories
IEEE Transactions on Systems, Man and Cybernetics
Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence
Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence
Exponential stability of delayed bi-directional associative memory networks
Applied Mathematics and Computation
Global asymptotic stability of delayed bi-directional associative memory neural networks
Applied Mathematics and Computation
Exponential stability and periodic oscillatory solution in BAM networks with delays
IEEE Transactions on Neural Networks
How delays affect neural dynamics and learning
IEEE Transactions on Neural Networks
Delay-independent stability in bidirectional associative memory networks
IEEE Transactions on Neural Networks
Exponential p-stability of impulsive stochastic Cohen-Grossberg neural networks with mixed delays
Mathematics and Computers in Simulation
Mathematics and Computers in Simulation
International Journal of Systems, Control and Communications
Mathematics and Computers in Simulation
Stability analysis for stochastic BAM neural networks with distributed time delays
ISNN'10 Proceedings of the 7th international conference on Advances in Neural Networks - Volume Part I
Mathematical and Computer Modelling: An International Journal
Hi-index | 7.29 |
A bidirectional associative memory neural network model with distributed delays is considered. By constructing a new Lyapunov functional, employing the homeomorphism theory, M-matrix theory and the inequality a@?"k"="1^mb"k^q^"^k==0,b"k=0,q"k0 with @?"k"="1^mq"k=r-1, and r1), a sufficient condition is obtained to ensure the existence, uniqueness and global exponential stability of the equilibrium point for the model. Moreover, the exponential converging velocity index is estimated, which depends on the delay kernel functions and the system parameters. The results generalize and improve the earlier publications, and remove the usual assumption that the activation functions are bounded . Two numerical examples are given to show the effectiveness of the obtained results.