Constructive Neural Network Learning Algorithms for Multi-Category Pattern Classification

Constructive learning algorithms offer an approach for incremental construction of potentially near-minimal neural network architectures for pattern classification tasks. Such algorithms help overcome the need for adhoc and often inappropriate choice of network topology in the use of algorithms that search for a suitable weight setting in an otherwise a-priori fixed network architecture. Several such algorithms proposed in the literature have been shown to converge to zero classification errors (under certain assumptions) on a finite, non-contradictory training set in a 2-category classification problem. This paper explores multi-category extensions of several constructive neural network learning algorithms for pattern classification. In each case, we establish the convergence to zero classification errors on a multi-category classification task (under certain assumptions). Results of experiments with non-separable multi-category data sets demonstrate the feasibility of this approach to multi-category pattern classification and also suggest several interesting directions for future research. Disciplines Artificial Intelligence and Robotics | Systems Architecture | Theory and Algorithms This article is available at Iowa State University Digital Repository: http://lib.dr.iastate.edu/cs_techreports/145 Constructive Neural Network Learning Algorithms for Multi-Category Pattern Classi cation Technical Report TR95-15 Rajesh Parekh, Jihoon Yang, and Vasant Honavar Arti cial Intelligence Research Group Department of Computer Science 226 Atanaso Hall, Iowa State University, Ames, IA 50011. U.S.A. [email protected] October 6, 1995