Question

Which of the following statements below is true about supervised/unsupervised machine learning?

Option 1: Supervised learning requires labeled training data, while unsupervised learning does not.
Option 2: Unsupervised learning always involves a predefined set of output classes.
Option 3: Supervised learning is primarily used for clustering tasks.
Option 4: Unsupervised learning is not suitable for regression problems.

Answer 1

The true statement among the provided options is that supervised learning algorithms require labeled training data, while unsupervised learning does not. Unsupervised learning is typically used for clustering and discovering hidden patterns in the data, without any pre-defined output classes.

Step-by-step explanation:

The true statement regarding supervised and unsupervised machine learning is: Option 1: Supervised learning requires labeled training data, while unsupervised learning does not. Supervised learning algorithms are trained on a labeled dataset, which means that each training example is paired with an output label. This approach is used for tasks where the prediction model needs to be taught the correct output, such as classification and regression problems.

In contrast, unsupervised learning algorithms are used when there is no labeled data available. These algorithms identify patterns and structure in the input data without reference to known, pre-defined output labels, making them suitable for tasks like clustering and association.

Option 2 is incorrect because unsupervised learning does not work with pre-defined output classes, as this is a characteristic of supervised learning. Option 3 is wrong as clustering tasks are typically the domain of unsupervised learning, not supervised learning. Lastly, Option 4 is untrue because unsupervised learning can be applied to regression problems when the regression is meant to understand relationships and structure in the data without labeled outputs.