Abstract. Imitation learning is a powerful approach to humanoid behavior generation, however, the most existing methods assume the availability of the information on the internal s...
Abstract. Multiple-instance learning (MIL) allows for training classifiers from ambiguously labeled data. In computer vision, this learning paradigm has been recently used in many ...
Abstract. The behaviorist view of learning that informs much of traditional schooling is not likely to invite students and teachers to see errors in a positive light. This is parti...
Abstract. Common inductive learning strategies offer the tools for knowledge acquisition, but possess some inherent limitations due to the use of fixed bias during the learning p...
Ciro Castiello, Giovanna Castellano, Anna Maria Fa...
This paper investigates the problem of improving the performance of general state-of-the-art robot control systems by autonomously adapting them to specific tasks and environments...