Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1016/j.patrec.2010.05.017 | Pattern Recognition Letters |
Keywords | Field | DocType |
three-dimensional entropy space,confusion matrix,information-theoretic tool,contingency table,multi-class classifier,balance equation,de finetti diagram,entropy triangle,performance measure,interesting property,entropic measure,three dimensional | Information theory,Confusion matrix,De Finetti diagram,Random subspace method,Diagram,Contingency table,Balance equation,Artificial intelligence,Classifier (linguistics),Mathematics,Machine learning | Journal |
Volume | Issue | ISSN |
31 | 12 | Pattern Recognition Letters |
Citations | PageRank | References |
6 | 0.53 | 9 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Francisco J. Valverde-Albacete | 1 | 116 | 20.84 |
Carmen Peláez-moreno | 2 | 130 | 22.07 |