%0 Journal Article
%T Field Theory Based Adaptive Resonance Neural Network Classifier<br>基于域理论的自适应谐振神经网络分类器
%A ZHOU Zhi-hua
%A CHEN Zhao-qian
%A CHEN Shi-fu
%A <br>周志华
%A 陈兆乾
%A 陈世福
%J 软件学报
%D 2000
%I 
%X A field theory based adaptive resonance neural network model, FTART2, is proposed in this paper. FTART2 combines the advantages of the adaptive resonance theory and the field theory, and achieves fast learning, strong generality and high efficiency. Moreover, FTART2 can adaptively adjust its network topology so that the disadvantage of manually configuring hidden neurons of traditional feed-forward networks is avoided. Benchmark tests show that FTART2 achieves higher accuracy and faster speed than standard BP.
%K Neural network
%K machine learning
%K competitive learning
%K classification
%K adaptive resonance theory
%K field theory<br>神经网络
%K 机器学习
%K 竞争学习
%K 分类
%K 自适应谐振理论
%K 域理论.
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=7735F413D429542E610B3D6AC0D5EC59&aid=6E816C90FD8CE4A3&yid=9806D0D4EAA9BED3&vid=708DD6B15D2464E8&iid=94C357A881DFC066&sid=06DAE5E1DF7D0B6A&eid=B7DE0F3CA34DA149&journal_id=1000-9825&journal_name=软件学报&referenced_num=11&reference_num=7