Conceptual clustering plays an important role in machine learning. In this paper, we propose a quasi-clustering method, network classification, which improves upon the computational efficiency of traditional conceptual clustering methods. Network classification is based on the Power Law assumption and the concept of hub observations/instances. The method is evaluated in several domains and compared with examples of both unsupervised learning and supervised learning methods. The results show that network classification maintains a comparable forecasting accuracy, while exhibiting an improved computing performance over conceptual clustering methods.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
Document Type: Research Article
Affiliations: The University of North Carolina at Charlotte College of Information Technology Charlotte NC 28223 USA
Publication date: January 1, 2005