Knowledge Discovery with Explained Case-Based Reasoning

摘要: The goal of Knowledge Discovery is to extract knowledge from a set data. Most common techniques used in discovery are clustering methods, whose analyze objects and obtain clusters based on the similarity among these objects. A desirable characteristic results that should be easily understandable by domain experts. In fact, characteristics exhibit eager learning methods (such as ID3) lazy when for building theories. this paper we propose LazyCL, procedure using method produce explanations unlabeled cases. analysis relations converges correct data set.