%0 Journal Article
%T New Conditions for Global Exponential Stability of Delayed Bidirectional Associative Memory Neural Network<br>时滞双向联想记忆神经网络的全局指数稳定新条件
%A WANG Kun-Lun
%A YUAN Min
%A CHEN Ling
%A <br>王昆仑
%A 袁暋
%A 陈凌
%J 计算机科学
%D 2006
%I 
%X By employing the inequality(?)and con- structing a new Lyapunov functional,we give a family of new sufficient conditions for global exponential stability of the delayed bidirectional associative memory neural network.The results allow for the consideration of all unbounded neu- ron activation functions(but not necessarily surjective),in particular,can analyze the exponential stability for the line- ar bidirectional associative memory neural network.Moreover,these conditions obtained are independent of delays and possess infinitely adjustable real parameters,which are of highly important significance in the designs and applications of BAM network.An example is also worked out to demonstrate the advantages of our results and give some analysis on the rapidity of convergence for BAM neural network.
%K Bidirectional associative memory
%K Global exponential stability
%K Neural network
%K Lyapunov functional<br>双向联想记忆
%K 全局指数稳定性
%K 神经网络
%K 李雅普洛夫泛涵
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=64A12D73428C8B8DBFB978D04DFEB3C1&aid=13E28514C3A73572&yid=37904DC365DD7266&vid=27746BCEEE58E9DC&iid=E158A972A605785F&sid=EF27C460877D3C9F&eid=334E2BB8B9A55ABB&journal_id=1002-137X&journal_name=计算机科学&referenced_num=0&reference_num=20