Abstract--Acquisition of new sensorimotor knowledge by imitation is a promising paradigm for robot learning. To be effective, action learning should not be limited to direct replic...
Many current medical image analysis problems involve learning thousands or even millions of model parameters from extremely few samples. Employing sparse models provides an effecti...
Wepropose a cooperative conceptual modelling environment in which two agents interact : the machineand the humanexpert. Theformer is able to extract knowledge from data using a sy...
—This paper presents a method for learning decision theoretic models of human behaviors from video data. Our system learns relationships between the movements of a person, the co...
Abstract. We propose a novel framework of autonomic intrusion detection that fulfills online and adaptive intrusion detection in unlabeled audit data streams. The framework owns a...