Machine Learning in Elixir

Using Clustering

In addition to supervised methods, Scholar offers a number of tools for unsupervised learning and analysis. Recall from Chapter 1, ​Make Machines That Learn​, that unsupervised learning is a type of machine learning where you learn only from inputs without access to any target information. Perhaps the most common type of unsupervised learning is clustering. Clustering is the process of identifying clusters or groups of similar data points in a dataset. There are many approaches to clustering, such as K-Means clustering, hierarchical clustering, spectral clustering, and more.

The most common type of clustering you’ll likely see in practice is K-Means clustering, which randomly assigns K centroids to random points in the dataset ...