We present a new learning machine model for classification problems, based on decompositions of multi-class classification problems in sets of two-class subproblems, assigned to non-linear dichotomizers that learn their task independently of each other. The experimentation performed on classical data sets, shows that this learning machine model achieves significant performance improvements over MLP, and previous classifiers models based on decomposition of polychotomies into dichotomies. The theoretical reasons of the good properties of generalization of the proposed learning machine model are explained in the framework of the statistical learning theory.