L1-norm-based kernel entropy components

作者：

Highlights：

• L1-KECA can achieve desirable performance on kernel density estimation.

• L1-KECA can obtain acceptable results on classification and face recognition.

• L1-KECA has much faster convergence than optimized KECA.

摘要

•L1-KECA can achieve desirable performance on kernel density estimation.•L1-KECA can obtain acceptable results on classification and face recognition.•L1-KECA has much faster convergence than optimized KECA.

论文关键词：Kernel entropy component analysis,Density estimation,Dimensionality reduction,Feature extraction,L1-norm

论文评审过程：Received 14 March 2019, Revised 20 July 2019, Accepted 31 July 2019, Available online 31 July 2019, Version of Record 6 August 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.106990