Quantifying and Visualizing Attribute Interactions: interaction information satisfies McGill's recursion and decomposes total correlation, which vanishes exactly under mutual independenceResearch Paper
Mutual information measures how much two attributes of a data set depend on each other. A pair of numbers does not describe three attributes. In the exclusive or, , each pair is independent while the triple is fully determined. A triplicated attribute, , is the opposite case: every pair is fully dependent, and given one attribute the other…