摘要
在近十几年里 ,已提出了一类与双向联想记忆相联系的神经网络模型 ,这些模型推广了单层自联想Hebbian相关器为两层异联想模式匹配器 ,因而 ,这类网络在模式识别、信号与图像处理等领域中有广阔的应用前景 研究了带离散时滞杂交双向联想记忆神经网络的收敛特性 ,利用Halanay型不等式获得了网络全局指数稳定性的充分条件 ,所得结果是与时滞无关的 ;已证明利用Halanay型不等式获得的结果改进了由Lyapunov方法获得的结果 ,而且获得的结果容易判定 。
During recent decades, a class of neural networks related to bi directional associative memory(BAM) have been proposed These models generalized the single layer autoassociative Hebbian correlator to a two layer pattern matched heteroassociative circuit Therefore, this class of networks possesses good application prospects in the areas of pattern recognition, signal and image processing, etc In this paper, convergence characteristics of hybrid bi directional associative memory neural networks with discrete delays are investigated Halanay type inequalities are employed to obtain delay independent sufficient conditions for the networks to converge exponentially toward the equilibria associated with the constant input sources It is shown that the estimates obtained from the Halanay type inequalities improve the estimates obtained from the Lyapunov methods The results are easily verified and a numerical example is given to illustrate the correctness of the results obtained
出处
《计算机研究与发展》
EI
CSCD
北大核心
2003年第10期1409-1413,共5页
Journal of Computer Research and Development
基金
国家自然科学基金 ( 60 2 710 19)
教育部博士点专项基金( 2 0 0 2 0 6110 0 7)
重庆市科委应用基础研究项目基金( 73 70 )
关键词
双向联想记忆
神经网络
全局指数稳定性
时滞
Halanay型不等式
bi directional associative memory
neural networks
global exponential stability
time delays
Halanay type inequalities
