Which learning paradigm uses historical labeled examples to learn a mapping from inputs to outputs?

Which learning paradigm uses historical labeled examples to learn a mapping from inputs to outputs?

• A. Supervised learning.
• B. Unsupervised learning.
• C. Reinforcement learning.
• D. Heuristic rules.

Answer: (A)

Learning from labeled data to map inputs to outputs is what supervised learning does. In this approach, models are trained on historical examples where each input is paired with the correct output label. By learning from many such labeled pairs, the model discovers a function that can predict outputs for new, unseen inputs. This is distinct from unsupervised learning, which seeks structure without labels; reinforcement learning, which learns by interacting with an environment and receiving rewards; and heuristic-rule approaches, which rely on manually crafted rules rather than data-driven learning.

Learning from labeled data to map inputs to outputs is what supervised learning does. In this approach, models are trained on historical examples where each input is paired with the correct output label. By learning from many such labeled pairs, the model discovers a function that can predict outputs for new, unseen inputs. This is distinct from unsupervised learning, which seeks structure without labels; reinforcement learning, which learns by interacting with an environment and receiving rewards; and heuristic-rule approaches, which rely on manually crafted rules rather than data-driven learning.