Proposing a Growing Self-Organizing Map Based on a Learning Theory of a Gaussian Mixture Model

Abstract

This study aims to develop a learning algorithm for increasing a learning speed and stability in a growing self-organizing map. In this presentation, I propose the growing self-organizing map based on a learning theory of a gaussian mixture model. In the proposed method, a stability of a leaning result is increased compared with conventional methods, because the new node is inserted based on the theory. Moreover, the growing speed of the network is fast.