Guided construction of training data set for neural networks

In this paper, we present an algorithm that selects a minimum set of exemplars that can be used to train a neural network. Specifically, we address potential relationships (i.e. modelling) between chemical structure and activity (quantitative structure-activity relationships) associated with doping control on athletes. Our focus is to derive a training set of exemplars which ensure that the training of a neural network-based model results in a system capable of generalization.