An online incremental orthogonal component analysis method for dimensionality reduction

详细信息    查看全文

• 作者：Tao Zhu^a ; ^{tao144@gmail.com} ; Ye Xu^b ; ¹ ; ^{ye@cs.dartmouth.edu} ; Furao Shen^a ; ^{frshen@nju.edu.cn} ; Jinxi Zhao^a ; ^{jxzhao@nju.edu.cn}
• 关键词：Dimensionality reduction ; Orthogonal component ; Incremental learning ; Automatic target dimension estimation ; Online learning
• 刊名：Neural Networks
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：85
• 期：Complete
• 页码：33-50
• 全文大小：1670 K
• 卷排序：85

文摘

In this paper, we introduce a fast linear dimensionality reduction method named incremental orthogonal component analysis (IOCA). IOCA is designed to automatically extract desired orthogonal components (OCs) in an online environment. The OCs and the low-dimensional representations of original data are obtained with only one pass through the entire dataset. Without solving matrix eigenproblem or matrix inversion problem, IOCA learns incrementally from continuous data stream with low computational cost. By proposing an adaptive threshold policy, IOCA is able to automatically determine the dimension of feature subspace. Meanwhile, the quality of the learned OCs is guaranteed. The analysis and experiments demonstrate that IOCA is simple, but efficient and effective.