Regularized discriminant entropy analysis

作者：

Highlights：

• We propose the regularized discriminant entropy (RDE).

• The RDE is based on the within-class entropy and robust estimation.

• We design a supervised algorithm, regularized discriminant entropy analysis (RDEA).

• RDEA can be regarded as a framework for supervised feature extraction.

摘要

•We propose the regularized discriminant entropy (RDE).•The RDE is based on the within-class entropy and robust estimation.•We design a supervised algorithm, regularized discriminant entropy analysis (RDEA).•RDEA can be regarded as a framework for supervised feature extraction.

论文关键词：Regularized discriminant entropy,Entropy-based learning,Discriminant entropy analysis

论文评审过程：Received 3 September 2012, Revised 4 August 2013, Accepted 23 August 2013, Available online 5 September 2013.

论文官网地址：https://doi.org/10.1016/j.patcog.2013.08.020