On the learning of weights in some aggregation operators: the weighted mean and OWA operators

We study the determination of weights for two types of aggregation operators: the weighted mean and the OWA operator. We assume that there is at our disposal a set of examples for which the outcome of the
aggregation operator is known. In the case of the OWA operator, we compare the results obtained by our method with another one in the literature. We show that the optimal weighting vector is reached with less cost.