Please use this identifier to cite or link to this item:
https://doi.org/10.1016/j.neucom.2009.12.032
Title: | Principal component analysis based on non-parametric maximum entropy | Authors: | He, R. Hu, B. Yuan, X. Zheng, W.-S. |
Keywords: | Entropy Information theoretic learning PCA Subspace learning |
Issue Date: | Jun-2010 | Citation: | He, R., Hu, B., Yuan, X., Zheng, W.-S. (2010-06). Principal component analysis based on non-parametric maximum entropy. Neurocomputing 73 (10-12) : 1840-1852. ScholarBank@NUS Repository. https://doi.org/10.1016/j.neucom.2009.12.032 | Abstract: | In this paper, we propose an improved principal component analysis based on maximum entropy (MaxEnt) preservation, called MaxEnt-PCA, which is derived from a Parzen window estimation of Renyi's quadratic entropy. Instead of minimizing the reconstruction error either based on L2-norm or L1-norm, the MaxEnt-PCA attempts to preserve as much as possible the uncertainty information of the data measured by entropy. The optimal solution of MaxEnt-PCA consists of the eigenvectors of a Laplacian probability matrix corresponding to the MaxEnt distribution. MaxEnt-PCA (1) is rotation invariant, (2) is free from any distribution assumption, and (3) is robust to outliers. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed linear method as compared to other related robust PCA methods. © 2010 Elsevier B.V. | Source Title: | Neurocomputing | URI: | http://scholarbank.nus.edu.sg/handle/10635/82929 | ISSN: | 09252312 | DOI: | 10.1016/j.neucom.2009.12.032 |
Appears in Collections: | Staff Publications |
Show full item record
Files in This Item:
There are no files associated with this item.
SCOPUSTM
Citations
34
checked on Jan 15, 2021
WEB OF SCIENCETM
Citations
28
checked on Jan 7, 2021
Page view(s)
137
checked on Jan 18, 2021
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.