%0 Journal Article
%T On weights and structure determination of Hermite-interpolation neural network<br>Hermite插值神经网络权值和结构确定理论探讨*
%A ZHANG Yu-nong
%A LI Ling-feng
%A GUO Dong-sheng
%A YANG Yi-wen
%A <br>张雨浓
%A 李凌峰
%A 郭东生
%A 杨逸文
%J 计算机应用研究
%D 2010
%I 
%X In order to overcome the inherent drawbacks of BP neural network, based on the Hermite-interpolation theory,this paper constructed a novel type of feed-forward neural-network model,which could be termed as Hermite-interpolation neural-network model.For this model,it presented a pseudo-inverse based weights determination method (or termed,weights-direct-determination method);and further investigated the determination of the hidden-layer neuron number(i.e.,structure-automatic-determination method).Computer-simulation results demonstrate that the presented Hermite-interpolation neural network with the above two methods can converge faster,and has a better testing performance(as compared to BP neural network), as well as the great de-noising and forecasting capabilities.
%K feed-forward neural network
%K Hermite interpolation
%K weights-direct-determination
%K structure-automatic-determination
%K BP neural network<br>前向神经网络
%K Hermite插值
%K 权值直接确定方法
%K 网络结构自确定方法
%K BP神经网络
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=A9D9BE08CDC44144BE8B5685705D3AED&aid=9DA4191282AB92F4BFB9B3B277D7F6A9&yid=140ECF96957D60B2&vid=DB817633AA4F79B9&iid=708DD6B15D2464E8&sid=8188F6E61BA745EB&eid=68F691920C8EF75B&journal_id=1001-3695&journal_name=计算机应用研究&referenced_num=0&reference_num=13