AWS Certified AI Practitioner Practice Exam

How does supervised learning differ from unsupervised learning?

1. Supervised learning uses labelled data, while unsupervised does not

2. Supervised learning is faster than unsupervised learning

3. Unsupervised learning only deals with classification tasks

4. Supervised learning requires a larger dataset

The correct answer is: Supervised learning uses labelled data, while unsupervised does not

Supervised learning is characterized by the use of labeled data, meaning that the training dataset includes both input features and the corresponding output labels that the model is expected to predict. This labeling allows the model to learn the relationship between inputs and outputs, making predictions based on the provided examples. In contrast, unsupervised learning operates on datasets that do not have labeled outputs. Instead of learning from explicit examples, the model identifies patterns, structures, or groupings within the data without any guidance. This approach is beneficial for tasks such as clustering and dimensionality reduction, where the goal is to explore the inherent structure of the data rather than predict a specific outcome. The other options do not accurately describe the fundamental differences between supervised and unsupervised learning. While supervised learning can sometimes be more efficient in training with a larger labeled dataset, it's not inherently faster than unsupervised learning, as speed can depend on several factors including the specific algorithms used. Unsupervised learning is not limited to classification tasks; it can also include regression and clustering. Finally, the size of the dataset required for supervised learning can vary widely based on the complexity of the task, and it isn’t strictly true that it always requires a larger dataset than unsupervised learning.