eXplainable Ensemble Strategy using distinct and restrict learning biases: A case study on the Brazilian Forest

Tatiane Nogueira Rios, Ricardo Araújo Rios, Rodrigo Fernandes de Mello

Abstract: Highlights•New ensemble approach that combines different supervised learning algorithms.•It uses distinct learning biases to comprise different empirical risks.•Fuzzy rules supports symbolic reasoning to understand every learning bias influences.•Results improved the overall classification and model interpretation.