User:3mta3

Hmmm

Topics related to conditional probability: conditional probability, conditioning (probability), conditional probability distribution, conditional expectation, regular conditional probability

Clustering

 * cluster analysis
 * clustering high-dimensional data
 * cluster analysis (in marketing)
 * Determining the number of clusters in a data set

Related concepts

 * Dimension reduction
 * Unsupervised learning
 * Density estimation

Main types

 * k-means clustering
 * Lloyd's algorithm
 * Linde-Buzo-Gray algorithm
 * k-medoids
 * hierarchical clustering
 * Single-linkage clustering
 * UPGMA
 * mixture model
 * Chinese restaurant process
 * Dirichlet process
 * Pitman–Yor process

Applications

 * Segmentation (image processing)
 * Thresholding (image processing)
 * Otsu's method
 * cluster analysis (in marketing) (above)
 * Market segment
 * Cluster sampling
 * Microtargeting
 * Document clustering
 * Latent Dirichlet allocation
 * Psychometrics
 * Pathfinder Networks

Other

 * Biclustering
 * Canopy clustering algorithm (not really an algorithm, more a heuristic for speeding up)
 * Constrained clustering (requires certain pairs either must or must not be in same cluster)
 * Conceptual clustering
 * Cobweb (clustering)
 * Formal concept analysis
 * Fuzzy clustering
 * Fuzzy c-means on cluster analysis
 * Spectral clustering on cluster analysis
 * Locality sensitive hashing
 * Artificial neural network (mention, but no explanation)

Comparison

 * Silhouette (clustering) (graphical representation)
 * Cophenetic correlation
 * Rand index
 * Adjusted rand index
 * Mutual information
 * Adjusted Mutual Information

Unknown

 * Consensus clustering (doesn't really explain what it is)
 * Information bottleneck method
 * Correlation clustering

Algorithms
N for novel (i.e. vanity page for CS paper), N? for possibly novel
 * Ants sleeping model N
 * birch (data clustering) N
 * Cure data clustering N
 * Cluster-weighted modeling N?
 * DBSCAN
 * FLAME clustering N
 * Girvan-Newman algorithm
 * k-means++ N? (for choosing starting points for k-means)
 * Neighbourhood components analysis N
 * OPTICS algorithm N?
 * QT (quality threshold) clustering on cluster analysis
 * SUBCLU N?