The use of entropy to measure structural diversity - Computer Science > LearningReport as inadecuate




The use of entropy to measure structural diversity - Computer Science > Learning - Download this document for free, or read online. Document in PDF available to download.

Abstract: In this paper entropy based methods are compared and used to measurestructural diversity of an ensemble of 21 classifiers. This measure is mostlyapplied in ecology, whereby species counts are used as a measure of diversity.The measures used were Shannon entropy, Simpsons and the Berger Parkerdiversity indexes. As the diversity indexes increased so did the accuracy ofthe ensemble. An ensemble dominated by classifiers with the same structureproduced poor accuracy. Uncertainty rule from information theory was also usedto further define diversity. Genetic algorithms were used to find the optimalensemble by using the diversity indices as the cost function. The method ofvoting was used to aggregate the decisions.



Author: L. Masisi, V. Nelwamondo, T. Marwala

Source: https://arxiv.org/



DOWNLOAD PDF




Related documents