14.3. Fuzzy Clustering Algorithms
One of the difficulties associated with the previously discussed probabilistic algorithms is the involvement of the pdf's, for which a suitable model has to be assumed. In addition, it is not easy to handle cases where the clusters are not compact but are shell shaped. A family of clustering algorithms that emancipates itself from such constraints is that of fuzzy clustering algorithms. These schemes have been the subject of intensive research during the past three decades. The major point that differentiates the two approaches is that in the fuzzy schemes a vector belongs simultaneously to more than one cluster, whereas in the probabilistic schemes, each vector belongs exclusively to a single cluster.
As ...
Get Pattern Recognition, 4th Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
