Given a database with missing or uncertain content, our goal is to correct and fill the database by extracting specific information from a large corpus such as the Web, and to d...
Abstract a paradigm of modern Machine Learning (ML) which uses rewards and punishments to guide the learning process. One of the central ideas of RL is learning by “direct-online...
Object detectors are typically trained on a large set of still images annotated by bounding-boxes. This paper introduces an approach for learning object detectors from realworld w...
Alessandro Prest, Christian Leistner, Javier Civer...
In multi-agent planning environments, action models for each agent must be given as input. However, creating such action models by hand is difficult and time-consuming, because i...
In recent years, there is a growing interest in developing online collaborative learning environments. In a learner-centered online collaborative environment, students work togeth...