A self-organizing neural tree for large-set pattern classification

Neural networks have been successfully applied to various pattern classification problems owing to their learning ability, high discrimination power, and excellent generalization ability. However, for the case of classifying patterns which are large-set and require complex decision boundaries in high-dimensional pattern space, the greater part of conventional neural networks suffer from some of difficult problems to solve, such as the structure and size of the network, the computational complexity, and so on. In this paper, to cope with these difficulties, we propose a new self-organizing neural tree and its learning algorithm. The basic idea is to partition pattern space hierarchically using the tree-structured network composed of subnetworks with topology-preserving mapping ability.