What distinguishes supervised learning from unsupervised learning?

Supervised learning is characterized by the presence of labeled data, meaning that the input data used to train the model comes with corresponding output labels. This allows the model to learn the relationship between the input features and the correct output during the training process. As the model is exposed to these labeled examples, it can effectively map inputs to outputs, enabling it to make predictions or classifications based on new, unseen data.

In contrast, unsupervised learning operates on datasets that do not have labeled outputs. In this approach, the algorithm tries to find hidden patterns or intrinsic structures within the input data without any guidance. The absence of labels means the model does not have specific outcome examples to learn from, making the objectives and methodologies of unsupervised learning distinctly different.

While both methodologies can involve the ability to learn patterns, the critical distinction lies in whether the data is labeled, which is foundational to the supervised learning paradigm.