From the course: AWS Certified Machine Learning Engineer Associate (MLA-C01) Cert Prep

Unlock this course with a free trial

Join today to access over 24,700 courses taught by industry experts.

Hierarchical clustering

Hierarchical clustering

- [Presenter] Hello, guys, and welcome again. So, in today's session, we are going to talk about the hierarchical clustering, which is an unsupervised learning clustering algorithm. So, first of all, the hierarchical clustering is an unsupervised learning algorithm, which is used to group similar objects into clusters, forming a hierarchy of clusters. This method is particularly suited for hierarchical data such as taxonomies. So, now, let's talk about the types of hierarchical clustering. So, you have the bottom-up approach, which is the agglomerative, and the top-down approach, which is the divisive. Let's talk about the agglomerative approach. So, in this approach, we are going to start with each data point as a single cluster, and then merge the closest pairs of clusters iteratively until all the points are in one single cluster. So, we would begin with each data point as its own cluster. We would find the two closest clusters and merge 'em together, and then we would iterate this…

Contents