Now showing items 1-2 of 2

    • Meta Clustering 

      Caruana, Rich; Elhawary, Mohamed; Nguyen, Nam; Smith, Casey (Cornell University, 2006-09-29)
      Clustering is ill-defined. Unlike supervised learning where labels lead to crisp performance criteria such as accuracy and squared error, clustering quality depends on how the clusters will be used. Devising clustering ...
    • Visualizing Metaclusters 

      Smith, Casey (2008-05-28)
      Metaclustering results in many alternate clusterings of a single data set, only a few of which may be useful to a specific user. Examining clusterings often is difficult, and asking a user to search through many different ...