A New Way for Hierarchical and Topological Clustering

Abstract

Clustering is one of the most important unsupervised learning problems. It deals with finding a structure in a collection of unlabeled data points. Hierarchical clustering algorithms are typically more effective in detecting the true clustering structure of a structured data set than partitioning algorithms. We find in literature several important research in hierarchical cluster analysis [Jain et al., 1999]. Hierarchical methods can be further divided to agglomerative and divisive algorithms, corresponding to bottom-up and top-down strategies, to build a hierarchical clustering tree. Another works concerning hierarchical classifiers are presented in [Jiang et al., 2010]. In this paper we propose a new way to build a set of self-organized hierarchical trees.KeywordsCost FunctionChild NodeRand IndexHierarchical Cluster AlgorithmTopological ClusterThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.