英和和英

出典:『Wikipedia』 (2010/12/05 08:10 UTC 版)

英語による解説

引用

Correlation clustering operates in a scenario where the relationship between the objects is known instead of the actual representation of the objects. For example, given a signed graph G = (V,E) where the edge label indicates whether two nodes are similar (+) or different (−), the task is to cluster the vertices so that similar objects are grouped together. Unlike other clustering algorithms this does not require choosing the number of clusters k in advance because the objective, to minimize the disagreements, is independent of the number of clusters.