The evaluation of data sources using multivariate entropy tools
作者：
Highlights：
• We provide crucial insights into a recently proposed Shannon-type entropy balance equation for multivariate joint distributions.
• The decomposition can be plotted in an entropy ternary diagram.
• Each axis of the ternary diagram provides specific information about the distributions.
• We use both tools in the exploratory analysis of machine learning datasets.
• These tools are applicable to supervised and unsupervised tasks.
摘要
•We provide crucial insights into a recently proposed Shannon-type entropy balance equation for multivariate joint distributions.•The decomposition can be plotted in an entropy ternary diagram.•Each axis of the ternary diagram provides specific information about the distributions.•We use both tools in the exploratory analysis of machine learning datasets.•These tools are applicable to supervised and unsupervised tasks.
论文关键词：Machine learning evaluation,Dataset entropy,Multivariate entropy,Entropic measures,Exploratory analysis,Entropy ternary diagram,Entropy balance equation
论文评审过程：Received 13 July 2016, Revised 31 October 2016, Accepted 2 February 2017, Available online 7 February 2017, Version of Record 16 February 2017.
论文官网地址：https://doi.org/10.1016/j.eswa.2017.02.010
