A hybrid model to infer US-Japan trade relations

被引:0
|
作者
Kamimura, R [1 ]
Yoshida, T [1 ]
机构
[1] Tokai Univ, Informat Sci Lab, Kanagawa 2591292, Japan
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we propose a new neural model in which an information maximization and error minimization component are combined. Because information is maximized, information is compressed into networks in explicit ways, which enables us to discover salient features in input patterns. We applied this method to a problem of US-Japan trade relations. Experimental results confirmed that because of maximized information in competitive units, easily interpretable internal representations can be obtained.
引用
收藏
页码:1800 / 1804
页数:5
相关论文
共 50 条