השוואת שיטות

	הכללה מוערמת (Stacked Generalization)	Bagging Ensemble
תחום	למידת אנסמבל	למידת אנסמבל
משפחה	Machine learning	Machine learning
שנת המקור	1992	1996
הוגה השיטה	David Wolpert	Leo Breiman
סוג	meta-learning aggregation	parallel ensemble
מקור מכונן	Wolpert, D. H. (1992). Stacked generalization. Neural Networks, 5(2), 241-259.	Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123-140.
כינויים	stacking, meta-learning	bootstrap aggregating
קשורות	3	4
תקציר	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.	Bagging, short for bootstrap aggregating, is an ensemble method that reduces variance by training multiple copies of a single learning algorithm on different random subsets of the training data. Each subset is created via bootstrap sampling—randomly drawing samples with replacement. Predictions are combined through majority voting (classification) or averaging (regression). Introduced by Leo Breiman in 1996, bagging forms the foundation for random forests and is particularly effective for reducing overfitting in high-variance models.