Automatic face recognition has been mainly tackled by matching a new image to a set of previously computed identity models. The literature describes approximations where those identity models are based on a single sample or a set of them. However, face representation keeps being a topic of great debate in the psychology literature, with some recent results suggesting the use of an average image. In this paper, instead of restricting our system to a fixed and precomputed classifier, the system learns iteratively based on the experience extracted from each meeting. The experiments presented introduce the use of an exemplar average based approach. The results show similar performance to an approach based on the use of multiple exemplars per identity, but reducing storage and processing cost. The process is done autonomously, using an automatic face detection system that meets people, excepting the supervision provided by a human to confirm or correct each meeting classification suggested by the system.