AP聚类算法是基于数据点间的 信息传递 的一种聚类算法。与k-均值算法或k中心点算法不同，AP算法不需要在运行算法之前确定聚类的个数。AP算法寻找的 examplars 即聚类中心点是数据集合中实际存在的点，作为每类的代表-AP clustering algorithm is based on the　 information transfer　 between data points of a clustering algorithm. K- and k-means algorithm or algorithms, center, AP clustering algorithm does not need to determine the number before running the algorithm.　 Examplars　 That is the central point AP clustering algorithm to find the point in the data set actually exist, as a representative of each class