Kernel-based dimensionality reduction using Renyi's α-entropy measures of similarity

详细信息    查看全文

• 作者：A.M. Alvarez-Meza^a ; ^{amalvarezme@unal.edu.co}Author Vitae ; J.A. Lee^b ; ^{john.lee@uclouvain.be}Author Vitae ; Michel Verleysen^b ; ^{michel.verleysen@uclouvain.be}Author Vitae ; G. Castellanos-Dominguez^a ; ^{cgcastellanosd@unal.edu.co}Author Vitae
• 关键词：Dimensionality reduction ; Kernel methods ; Renyi's α-entropy
• 刊名：Neurocomputing
• 出版年：2017
• 出版时间：26 January 2017
• 年：2017
• 卷：222
• 期：Complete
• 页码：36-46
• 全文大小：2948 K
• 卷排序：222

文摘

A new dimensionality reduction method is proposed based on a kernel enhancement of stochastic neighborhood preservation. A Gramm matrix estimation of Renyi's alpha-entropy is involved as the cost function. The proposed approach is a data-driven framework for information theoretic learning.