%0 Journal Article
%T The pattern match learning of binary neural networks<br>二进神经网络的模式匹配学习
%A Lu Yang
%A Wei Zhen
%A Han Jianghong
%A Fan Yuqi
%A <br>陆阳
%A 魏臻
%A 韩江洪
%A 樊玉琦
%J 电子与信息学报
%D 2003
%I 
%X It is necessary to know the logical meaning of every binary neuron when extracting knowledge from a binary neural network. Generally, it is difficult to analyze learning results of a learning algorithm for binary neural networks. In this paper, a new learning method is presented which is based on analyzing a set of linear separable structures. The most important benefit of this method is all binary neurons belong to one or more types of linear separable structure sets. If those linear separable structure sets have clear logical meaning, the whole knowledge of binary neural networks can be dug out.
%K Binary neural networks
%K Linear separability
%K Pattern match<br>二进神经网络
%K 模式匹配
%K 线性可分
%K 分层表达
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=1319827C0C74AAE8D654BEA21B7F54D3&jid=EFC0377B03BD8D0EF4BBB548AC5F739A&aid=2504F3BB9C560D65&yid=D43C4A19B2EE3C0A&vid=C5154311167311FE&iid=CA4FD0336C81A37A&sid=67969BA850333433&eid=9C65ADEB5990B252&journal_id=1009-5896&journal_name=电子与信息学报&referenced_num=0&reference_num=7