Clustering Algorithms - Key Vocabulary

Vocabulary flashcards covering key clustering concepts and algorithms from the notes.

K-Means Clustering

A partitioning unsupervised algorithm that divides data into K non-overlapping clusters by minimizing the within-cluster sum of squares (inertia).

Inertia (Within-cluster Sum of Squares)

The sum of squared distances between data points and their cluster centroids; K-Means aims to minimize this value.

Hierarchical Clustering

Builds a hierarchy of clusters by recursively merging or splitting clusters; can be agglomerative (bottom-up) or divisive (top-down).

Agglomerative Clustering

A hierarchical approach that starts with each data point as its own cluster and merges clusters based on a linkage criterion (e.g., single, complete, average).

DBSCAN

Density-Based Spatial Clustering that groups densely packed points using ε (epsilon) and MinPts; handles noise and discovers clusters of arbitrary shape without predefining the number of clusters.

ε (epsilon) in DBSCAN

Maximum distance between two points for them to be considered neighbors.

MinPts

Minimum number of points required in a point's ε-neighborhood to form a dense region.

Core Point

A point with at least MinPts points within its ε-neighborhood (including itself).

Border Point

A point within the ε-neighborhood of a core point but not itself a core point.

Noise Point (Outlier)

A point that is neither a core point nor a border point and is not assigned to a cluster.

OPTICS

Ordering Points To Identify the Clustering Structure; extension of DBSCAN producing a hierarchical clustering structure and robustness to varying densities.

Mean Shift Clustering

Non-parametric algorithm that shifts centroids toward areas of higher data density to identify clusters.

Gaussian Mixture Models (GMM)

Model-based clustering assuming data are generated from a mixture of Gaussian distributions; estimates parameters to identify clusters.

Spectral Clustering

Graph-based clustering technique that uses the eigenvalues of a similarity matrix to partition data into clusters.