A topology based multi-classifier system

This paper introduces a new scheme for the general problem of classification task-solving by designing a multi-classifier system. The distribution process respects the data topology in the feature space in order to reach reliable decisions. To this end we use a self-organizing network which gives a graph that represents the data topology. During the decision process this graph is used to activate the appropriate classifiers among a set of committee experts. Comparative results are given for a handwritten digit recognition problem.