Previous chapters focused on supervised learning, where models learn from data containing predefined answers or labels. This chapter shifts focus to unsupervised learning, a different category of machine learning where the data lacks these explicit labels. The goal here is to find inherent structures or patterns within the data itself.

Specifically, we will look at clustering, a common unsupervised task aimed at grouping similar data points together. You will learn:

• The definition and purpose of unsupervised learning.
• The concept of clustering and its applications.
• How the K-Means algorithm works to partition data into a specified number of clusters, often denoted as $K$.
• Considerations for selecting the number of clusters ($K$).
• The steps involved in the K-Means process and some of its limitations.
• How to apply K-Means to a dataset in a practical exercise.

This chapter introduces the fundamentals of finding patterns in unlabeled data using the K-Means clustering technique.