CASIA OpenIR  > 模式识别国家重点实验室  > 多媒体计算与图形学
Robust C-Loss Kernel Classifiers
Xu, Guibiao1; Hu, Bao-Gang1; Principe, Jose C.2
Source PublicationIEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
2018-03-01
Volume29Issue:3Pages:510-522
SubtypeArticle
AbstractThe correntropy-induced loss (C-loss) function has the nice property of being robust to outliers. In this paper, we study the C-loss kernel classifier with the Tikhonov regularization term, which is used to avoid overfitting. After using the half-quadratic optimization algorithm, which converges much faster than the gradient optimization algorithm, we find out that the resulting C-loss kernel classifier is equivalent to an iterative weighted least square support vector machine (LS-SVM). This relationship helps explain the robustness of iterative weighted LS-SVM from the correntropy and density estimation perspectives. On the large-scale data sets which have low-rank Gram matrices, we suggest to use incomplete Cholesky decomposition to speed up the training process. Moreover, we use the representer theorem to improve the sparseness of the resulting C-loss kernel classifier. Experimental results confirm that our methods are more robust to outliers than the existing common classifiers.
KeywordCorrentropy Half-quadratic (Hq) Optimization Kernel Classifier Loss Function
WOS HeadingsScience & Technology ; Technology
DOI10.1109/TNNLS.2016.2637351
WOS KeywordSUPPORT VECTOR MACHINES ; LABEL NOISE ; DATA SETS ; CLASSIFICATION ; CORRENTROPY ; ALGORITHMS ; MINIMIZATION ; REGRESSION ; FRAMEWORK ; SIGNAL
Indexed BySCI
Language英语
Funding OrganizationNSFC(61273196 ; China Scholarship Council within Computational NeuroEngineering Laboratory ; 61573348)
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS IDWOS:000426344600001
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/19986
Collection模式识别国家重点实验室_多媒体计算与图形学
Affiliation1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Univ Florida, Dept Elect & Comp Engn, Computat NeuroEngn Lab, Gainesville, FL 32611 USA
Recommended Citation
GB/T 7714
Xu, Guibiao,Hu, Bao-Gang,Principe, Jose C.. Robust C-Loss Kernel Classifiers[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2018,29(3):510-522.
APA Xu, Guibiao,Hu, Bao-Gang,&Principe, Jose C..(2018).Robust C-Loss Kernel Classifiers.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,29(3),510-522.
MLA Xu, Guibiao,et al."Robust C-Loss Kernel Classifiers".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 29.3(2018):510-522.
Files in This Item: Download All
File Name/Size DocType Version Access License
Robust C-Loss Kernel(3169KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xu, Guibiao]'s Articles
[Hu, Bao-Gang]'s Articles
[Principe, Jose C.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xu, Guibiao]'s Articles
[Hu, Bao-Gang]'s Articles
[Principe, Jose C.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xu, Guibiao]'s Articles
[Hu, Bao-Gang]'s Articles
[Principe, Jose C.]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Robust C-Loss Kernel Classifiers.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.