GENERALIZED FUZZY KOHONEN CLUSTERING NETWORKS

A fuzzy Kohonen clustering network was proposed which integrates the F uzzy c-means (FCM) model into the learning rate and updating strategie s of the Kohonen network. This yields an optimization problem related to FCM, and the numerical results show improved convergence as well as reduced labeling error. However, the clusters may be either hypersphe rical-shaped or hyperellipsoidal-shaped, we use a generalized objectiv e function involving a collection of linear varieties. In this way the model is distributed and consists of a series of 'local' linear-type models (based on the revealed clusters). We propose a method to genera lize the fuzzy Kohonen clustering networks. Anderson's IRIS data and t he artificial data set are used to illustrate this method; and results are compared with the standard Kohonen approach and the fuzzy Kohonen clustering networks.