%0 Journal Article
%T Complex-exponential Fourier neuronal network and its hidden-neuron growing algorithm<br>复指数Fourier神经元网络隐神经元衍生算法
%A ZHANG Yu-nong
%A ZENG Qing-dan
%A XIAO Xiu-chun
%A JIANG Xiao-hua
%A ZOU A-jin
%A <br>张雨浓
%A 曾庆淡
%A 肖秀春
%A 姜孝华
%A 邹阿金
%J 计算机应用
%D 2008
%I 
%X Based on the approximation theory of Fourier-series working in square integrable space, a Fourier neuronal network was constructed by using activation functions of the complex exponential form. Then a weights-direct-determination method was derived to decide the neural-network weights immediately, which remedied the weaknesses of conventional BP neural networks such as small convergence rate, easily converging to local minimum and possibly lengthy or oscillatory learning process. A hidden-neurons-growing al...
%K Fourier series
%K weights-direct-determination
%K feed-forward neural network
%K growing algorithm
%K complex-exponent<br>Fourier级数
%K 前向神经网络
%K 权值直接确定
%K 衍生算法
%K 复指数
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=831E194C147C78FAAFCC50BC7ADD1732&aid=205A3BE098E3228C90D25D900B60C638&yid=67289AFF6305E306&vid=D3E34374A0D77D7F&iid=F3090AE9B60B7ED1&sid=B2AD9650C7AE1439&eid=2FC1DBE455F23123&journal_id=1001-9081&journal_name=计算机应用&referenced_num=4&reference_num=17