An ensemble learning method trains multiple weak learners sequentially, where each subsequent learner is trained to pay more attention to the training examples that previous learners misclassified. Which ensemble technique does this describe?

Boosting (e.g., AdaBoost, Gradient Boosting) is defined by its sequential training process: each new weak learner is trained on a re-weighted version of the data that emphasizes previously misclassified examples, and the learners' outputs are combined (often with weights reflecting each learner's accuracy). This is fundamentally different from Bagging/Random Forest, which train learners independently and in parallel on different bootstrap samples, then simply average or vote their predictions without any sequential error-correction mechanism.