What is AdaBoost weight update mechanism?

AdaBoost increases weights of misclassified samples so later models focus on harder cases.

AdaBoost initializes equal weights for all samples. After each weak learner, it calculates error rate and assigns higher weights to misclassified samples. The next learner focuses more on these difficult cases. Final prediction is a weighted sum of all weak learners based on their accuracy. This adaptive weighting reduces bias iteratively.