Parallel non-linear dimension reduction algorithm on GPU

doi:10.1504/IJGCRSIS.2011.043370

淡江大學機構典藏 > 商管學院 > 資訊管理學系暨研究所 > 期刊論文 > Item 987654321/95752

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/95752

题名:	Parallel non-linear dimension reduction algorithm on GPU
作者:	Yeh, Tsung-Tai;Chen, Tseng-Yi;Chen, Yen-Chiu;Wei, Hsin-Wen
贡献者:	淡江大學電機工程學系
关键词:	nonlinear dimension reduction;dimensionality reduction;GPU;complex datasets;memory space;graphics processing unit
日期:	2011
上传时间:	2014-02-12 21:36:08 (UTC+8)
出版者:	Inderscience Publishers
摘要:	Advances in non-linear dimensionality reduction provide a way to understand and visualise the underlying structure of complex datasets. The performance of large-scale non-linear dimensionality reduction is of key importance in data mining, machine learning, and data analysis. In this paper, we concentrate on improving the performance of non-linear dimensionality reduction using large-scale datasets on the GPU. In particular, we focus on solving problems including k-nearest neighbour (KNN) search and sparse spectral decomposition for large-scale data, and propose an efficient framework for local linear embedding (LLE). We implement a k-d tree-based KNN algorithm and Krylov subspace method on the GPU to accelerate non-linear dimensionality reduction for large-scale data. Our results enable GPU-based k-d tree LLE processes of up to about 30-60? faster compared to the brute force KNN (Hernandez et al., 2007) LLE model on the CPU. Overall, our methods save O(n²-6n-2k-3) memory space.
關聯:	International Journal of Granular Computing, Rough Sets and Intelligent Systems 2(2), pp.149-165
DOI:	10.1504/IJGCRSIS.2011.043370
显示于类别:	[資訊管理學系暨研究所] 期刊論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	211	检视/开启

在機構典藏中所有的数据项都受到原著作权保护.

TAIR相关文章

数据加载中.....