%0 Journal Article
%T Knowledge Extension and Fault Recovery of Feed Forward Neural Networks<br>前馈网的知识扩充及故障恢复
%A SHI Jun
%A CHEN You-ping
%A Peter Wai-tat Tse
%A <br>石　俊
%A 陈幼平
%A Peter Wai-tat Tse
%J 控制理论与应用
%D 2000
%I 
%X Aiming at the problem of poor extensibility of feed forward neural networks,a knowledge extension method is proposed in this paper.Preserving the original neural networks,we can both retain existing training result and learn new knowledge by adding a new subnet.Simultaneously,the strategy of fault recovery of neural networks is studied and a fault compensation algorithm is given.The effectiveness of proposed algorithms is verified by numerical simulations.
%K FNN
%K learning
%K fault compensation<br>前馈网
%K 故障补偿
%K 知识扩充
%K 故障恢复
%K 神经网络
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=970898A57DFC021F93AB51667BAED7F7&aid=E2D189233E462D75&yid=9806D0D4EAA9BED3&vid=BCA2697F357F2001&iid=0B39A22176CE99FB&sid=3A0155B37D8FF829&eid=C29816B2656377A7&journal_id=1000-8152&journal_name=控制理论与应用&referenced_num=1&reference_num=6