Ensemble learning
Also: ensemble methods, ensembling, model ensemble
Training multiple models and aggregating them by voting, averaging or a learned combiner. It works best when members are accurate but make different mistakes; bagging mainly reduces variance and boosting mainly reduces bias.
Example
Three classifiers that are each 70% accurate and err independently give a majority vote that is right about 78% of the time (0.7³ + 3 · 0.7² · 0.3 ≈ 0.784).