Which machine learning approach is trained using data where each example includes the correct output labels?

Supervised learning is the correct answer because it involves training a model on a labeled dataset, meaning each input example is paired with its corresponding correct output. The model learns to map inputs to outputs by identifying patterns in these labeled examples. Unsupervised learning, in contrast, deals with unlabeled data, aiming to find hidden structures or patterns without explicit guidance (e.g., clustering). Reinforcement learning trains an agent to make decisions by interacting with an environment and receiving rewards or penalties, without pre-existing labeled data. Transfer learning involves reusing a pre-trained model from one task as a starting point for a new, related task, which may or may not involve labeled data for the new task, but the core definition of labeled input-output pairs for training applies specifically to supervised learning.