%0 Journal Article
%T Theoretical Analysis on Classification Capability of Classifier Containing Quadratic Sigmoid Neurons<br>一类二次Sigmoid神经元构建的分类器分类能力的理论分析
%A Wang Baoyun
%A He Zhenya
%A <br>王保云
%A 何振亚
%J 自动化学报
%D 1998
%I 
%X This paper addresses the classification capability of network containing quadratic sigmoidal neurons. By analysing the size of the network required for solving Dichotomy problem, we can figure out the degree of the improvement on the classification capability of net- work by using quadratic sigmoidal neurons.
%K Neuron model
%K dichotomy
%K threshold
%K classification capability<br>神经元模型
%K 二分类
%K 分类能力
%K 人工神经网络
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=E76622685B64B2AA896A7F777B64EB3A&aid=7E8E705BD00A5A79&yid=8CAA3A429E3EA654&vid=B91E8C6D6FE990DB&iid=B31275AF3241DB2D&sid=4AB2A4AB67F2B16E&eid=8C8D39B86A1EED4F&journal_id=0254-4156&journal_name=自动化学报&referenced_num=1&reference_num=3