%0 Journal Article
%T ANALYSIS AND IMPROVEMENT OF FTART ALGORITHM<br>对FTART算法的研究及改进
%A CHEN Zhaoqian
%A LI Hongbing
%A ZHOU Rong
%A CHEN Shifu
%A <br>陈兆乾
%A 李红兵
%A 周戎
%A 陈世福
%J 软件学报
%D 1997
%I 
%X FTART(field theory based ART) algorithm combines the theory of ART(adaptive resonance theory), ARTMAP and field theory. It corrects the generated classification regarding the supposed distribution possibility of examples in the instance space. FTART employes a different conflict resolve process and dynamicly expanding the classification area. By further studies, the paper improves the algorithm's ability of learning continuous function mappings. Some benchmark test results and the analysis are also given. They proved that FTART has good performance on pattern recognition and continuous function mapping.
%K Neural network
%K ARTMAP algorithm
%K continuous function mapping<br>神经网络
%K ARTMAP算法
%K 连续函数映射
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=7735F413D429542E610B3D6AC0D5EC59&aid=673F2FADCE6DF7FBE2403C8BF6149A74&yid=5370399DC954B911&vid=5D311CA918CA9A03&iid=E158A972A605785F&sid=0F7768518993EDDE&eid=FDC7AF55F77D8CD4&journal_id=1000-9825&journal_name=软件学报&referenced_num=8&reference_num=12