%0 Journal Article
%T Converging Hopfield Neural Network by Evolutionary Strategies<br>进化策略求解Hopfield神经网络
%A LI Ming
%A YAN Chao-hua
%A LIU Gao-hang
%A <br>黎 明
%A 严超华
%A 刘高航
%J 中国图象图形学报
%D 2000
%I 
%X The method of applying evolutionary strategies to converge Hop field neural network is proposed in this paper. Genetic search of evolutionary s trategies(ES) consists of three consecutive processes. ES performs local search in some small domain in the first process,and the search domain grows in the se cond process. Then ES performs the global search in whole domain in the third pr ocess. We use the dynamic equation to indicate the ES search direction to speed up the local search speed obviously. The ES search domain is small in the first process,and the second and the third process are based on the optimization resu lts of their previous processes,therefore the convergence speed of the proposed method is much faster and it needs less memory space.
%K Pattern recognition
%K Evolutionary strategies
%K Hopfield neural network
%K Optimiz ation<br>进化策略
%K Hopfield神经网络
%K 优化
%K 求解
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=D06194629680C940ACE75262F54B9D85&aid=FF481E46C3D76159&yid=9806D0D4EAA9BED3&vid=94C357A881DFC066&iid=DF92D298D3FF1E6E&sid=70E3F4DEB0172F14&eid=C7B13290323C226E&journal_id=1006-8961&journal_name=中国图象图形学报&referenced_num=0&reference_num=7