Which of the following best describes supervised learning?

A$.$ The model is trained using only input data, and it learns to generate output labels on its own.

B$.$ The model is trained using input data and corresponding output labels to learn a mapping from inputs to outputs.

C$.$ The model is trained without any labeled data, and it must find patterns and structure in the input data by itself.

D$.$ The model is trained using input data and some partially labeled data to improve its performance over time.