Adaptive lasso echo state network for time series prediction - 文章详情页

作者：

Zhao, Jing (Zhao, Jing.) (学者：赵京) | Wang, Lei (Wang, Lei.) | Yang, Cuili (Yang, Cuili.)

收录：

EI Scopus

摘要：

Echo　state　network　(ESN),　a　novel　recurrent　neural　network,　has　a　randomly　and　sparsely　connected　reservoir.　Since　the　reservoir　is　very　large,　the　collinearity　problem　may　exist　in　ESN.　To　overcome　this　problem　and　get　a　sparse　architecture,　an　adaptive　lasso　echo　state　network　(ALESN)　is　proposed,　in　which　the　adaptive　lasso　algorithm　is　used　to　calculate　the　output　weights.　The　proposed　ALESN　can　deal　with　the　collinearity　problem　and　has　the　oracle　property.　Simulation　results　show　that　the　proposed　ALESN　has　better　performance　and　more　compact　architecture　than　some　other　existing　methods.　©　2017　IEEE.

关键词：

Network architecture Time series Recurrent neural networks

作者机构：

[ 1 ] [Zhao, Jing]China National Institute of Standardization, Beijing, China
[ 2 ] [Wang, Lei]Faculty of Information Technology, Beijing University of Technology, Beijing, China
[ 3 ] [Yang, Cuili]Faculty of Information Technology, Beijing University of Technology, Beijing, China

通讯作者信息：

电子邮件地址：

查看成果更多字段

成果类型
所属机构

所有年份指定年份从至