What key factor distinguishes supervised learning from unsupervised learning?

Supervised learning is characterized by its reliance on labeled data, which is a fundamental distinction from unsupervised learning. In supervised learning, the algorithm is trained on a dataset that includes both the input features and the corresponding output labels, allowing it to learn the mapping between them. This training approach enables the algorithm to make predictions or classifications based on new, unseen data by applying what it has learned during training.

In contrast, unsupervised learning does not use labeled data; instead, it seeks to identify patterns or structures within the data without any explicit guidance regarding what the outputs should be. This can involve clustering the data into groups or reducing dimensions to find underlying relationships among the input features.

The other options do not accurately reflect the primary distinction between supervised and unsupervised learning. While it may be true that supervised learning often requires more computational power or can be faster in training times, these factors are not definitive characteristics that separate the two learning approaches. Additionally, supervised learning is not restricted to classification tasks; it can also be used for regression tasks, which further illustrates that the presence of labeled data is the key distinguishing feature.