Two Information-Theoretic Tools to Assess the Performance of Multi-Class Classifiers

We develop two tools to analyze the behavior of multiple-class, or multi-class, classifiers by means of entropic measures on their confusion matrix or contingency table. First we obtain a balance
equation on the entropies that captures interesting properties of the
classifier. Second, by normalizing this balance equation we first obtain
a 2-simplex in a three-dimensional entropy space and then the de
Finetti entropy diagram or entropy triangle. We also give examples of the assessment of classifiers with these tools.

Two Information-Theoretic Tools to Assess the Performance of Multi-Class Classifiers Articles