7.1. Classifiers using multiple samples of the dataset

AdaBoost Pros: Low generalization error, easy to code, works with most classifiers, no parameters to adjust Cons: Sensitive to outliers Works with: Numeric values, nominal values

You’ve seen five different algorithms for classification. These algorithms have individual strengths and weaknesses. One idea that naturally arises is combining multiple classifiers. Methods that do this are known as ensemble methods or meta-algorithms. Ensemble methods can take the form of using different algorithms, using the same algorithm with different settings, or assigning different parts of the dataset to different classifiers. We’ll next talk about two methods that use multiple instances of the same classifier and alter the dataset applied to these classifiers. Finally, we’ll discuss how to approach AdaBoost with our general framework for approaching machine-learning problems.