Comparer des méthodes

	Agrégation par décompte de Borda	Généralisation empilée
Domaine	Apprentissage ensembliste	Apprentissage ensembliste
Famille	Machine learning	Machine learning
Année d'origine	1781	1992
Auteur d'origine	Jean-Charles de Borda	David Wolpert
Type	rank-based aggregation	meta-learning aggregation
Source fondatrice	Borda, J. C. de (1781). Mémoire sur les élections au scrutin. Histoire de l'Académie Royale des Sciences.	Wolpert, D. H. (1992). Stacked generalization. Neural Networks, 5(2), 241-259.
Alias	weighted voting, rank aggregation	stacking, meta-learning
Apparentées	3	3
Résumé	Borda count is a preference aggregation method that combines ranked predictions from multiple classifiers by assigning points based on ranking position. Each classifier ranks the possible outcomes, and each class receives points inversely proportional to its rank position. The class with the highest total score is selected. Originally proposed by French mathematician Jean-Charles de Borda in 1781, this method has been adapted for ensemble learning to aggregate soft predictions and rank-ordered outputs.	Stacked generalization, or stacking, is a two-level ensemble method where base-level classifiers are trained on the original data, and a meta-learner is trained on the predictions of the base classifiers. The meta-learner learns how to best combine base predictions rather than using fixed aggregation rules. Introduced by David Wolpert in 1992, stacking achieves state-of-the-art performance by automatically learning the optimal weighting and interaction patterns among base models.