Title :
Global asymptotic stability analysis of bidirectional associative memory neural networks with time delays
Author_Institution :
Dept. of Comput. Eng., Istanbul Univ., Turkey
fDate :
5/1/2005 12:00:00 AM
Abstract :
This paper presents a sufficient condition for the existence, uniqueness and global asymptotic stability of the equilibrium point for bidirectional associative memory (BAM) neural networks with distributed time delays. The results impose constraint conditions on the network parameters of neural system independently of the delay parameter, and they are applicable to all continuous nonmonotonic neuron activation functions. It is shown that in some special cases of the results, the stability criteria can be easily checked. Some examples are also given to compare the results with the previous results derived in the literature.
Keywords :
asymptotic stability; content-addressable storage; delays; distributed parameter systems; neural nets; stability criteria; bidirectional associative memory neural network; continuous nonmonotonic neuron activation function; distributed time delays; global asymptotic stability analysis; stability criteria; Associative memory; Asymptotic stability; Delay effects; Design optimization; Magnesium compounds; Neural networks; Neurons; Stability analysis; Stability criteria; Sufficient conditions; Delayed neural networks; Lyapunov functionals; equilibrium and stability analysis; Algorithms; Computer Simulation; Information Storage and Retrieval; Linear Models; Neural Networks (Computer); Nonlinear Dynamics; Numerical Analysis, Computer-Assisted; Signal Processing, Computer-Assisted; Stochastic Processes; Time Factors;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2005.844910
