What best defines "Supervised Learning" in machine learning?

Supervised learning is best defined as the approach where a model is trained using labeled data. In this context, labeled data consists of input-output pairs, where the inputs are the features given to the model, and the corresponding outputs represent the recognized responses or classifications that the model should produce. This type of learning allows the model to map inputs to the correct outputs based on the examples it learns from.

The effectiveness of supervised learning comes from its reliance on the labeled dataset used during training, which directly informs the model on the relationship between variables and helps it make predictions or classifications on new, unseen data. This approach is commonly used in tasks such as classification and regression, where the goal is to predict categorical labels or continuous values, respectively.

In contrast, the other options describe different methods of learning. For instance, real-time learning without labeled data pertains to unsupervised learning or reinforcement learning, where the model learns from raw or unstructured data without predefined categories.