Supervised learning involves using labeled data to train a model to make predictions or classifications. The model learns by analyzing the relationships between input features and their corresponding output labels. This enables the model to generalize and predict outputs for new, unseen data. On the contrary, unsupervised learning is employed when there are no predefined labels in the dataset. In this case, the algorithm focuses on finding patterns, similarities, or anomalies in the data without explicitly knowing the desired output. Unsupervised learning is useful for tasks such as clustering or anomaly detection.

Supervised learning refers to a type of machine learning where labeled datasets are used to train a model to make predictions or classifications. The model learns by identifying patterns, relationships, and correlations between input variables and their corresponding output labels. This way, the model can be used to predict the output for new, unseen data. On the other hand, unsupervised learning is a technique used when the dataset does not have any predefined labels. The goal is to find patterns, structures, or relationships within the data. Without specific output labels, unsupervised learning algorithms group similar data points into clusters or identify anomalies.

In supervised learning, the algorithm is 'supervised' by providing both input data and the output labels to learn from. This allows the model to make predictions based on the training data. In contrast, unsupervised learning does not rely on any predefined labels. Instead, it explores the data to find hidden patterns, structures, or relationships. It is often used for exploratory analysis or to uncover insights in large datasets where it's difficult to manually label the data.