KI-Glossar
Das vollständige Wörterbuch der Künstlichen Intelligenz
Epsilon (ε)
Maximum distance parameter that defines the radius of the neighborhood around each point to determine local density.
MinPts
Parameter defining the minimum number of points required within the epsilon neighborhood for a point to be considered a core point.
Density-based clustering
Partitioning approach that identifies clusters as dense regions separated by regions of low density.
Arbitrary-shaped cluster
Ability of DBSCAN to identify clusters of non-convex shapes and variable sizes, unlike algorithms like K-means.
Outlier detection
Process of identifying observations that significantly deviate from the normal behavior of the data, realized as noise points in DBSCAN.
Density parameters
Set of hyperparameters (epsilon and MinPts) that control DBSCAN's sensitivity to the local density of the data.
OPTICS
Extension of DBSCAN that creates a clustering order allowing the extraction of density structures at different scales without a fixed epsilon parameter.
HDBSCAN
Hierarchical variant of DBSCAN that automatically adapts density parameters and allows for clusters of variable densities.
Connectivity graph
Theoretical representation of reachability relationships between core points that form the underlying structure of clusters in DBSCAN.