A New Statistical competitive Data Clustering Approaches: SRPCL and SRPCCL

摘要

Finding useful patterns in datasets has attracted considerable interest recently, and one of the most widely studied techniques is data clustering. Clustering is the unsupervised classification of patterns (observations, data items, or feature vectors) into clusters (groups) and it is one of the most important research and application areas of neural networks. This paper summarizes some of the most important developments in competitive learning algorithms for data clustering and presents two new fast learning approaches based on the competitive concept. The first one used the rival competitive learning (RPCL) concepts and the second one investigates the rival penalized controlled competitive learning (RPCCL) concepts, to dynamically control the rival-penalizing forces.