Vector Quantization / Kmeans
Clustering algorithms are useful in information theory, target detection,
communications, compression, and other areas. The vq module only
supports vector quantization and the k-means algorithms. Development
of self-organizing maps (SOM) and other approaches is underway.
Hierarchical Clustering
The hierarchy module provides functions for hierarchical and agglomerative
clustering. Its features include generating hierarchical clusters from
distance matrices, computing distance matrices from observation vectors,
calculating statistics on clusters, cutting linkages to generate flat
clusters, and visualizing clusters with dendrograms.
Distance Computation
The distance module provides functions for computing distances between
pairs of vectors from a set of observation vectors.