In this paper we present a new method, time-striding hidden Markov model (TSHMM), to learn from long-term motion for atomic behaviors and the statistical dependencies among them. T...
In this contribution we present the dialogue generator module of a Dialogue-based Interactive Diagnostic and Learning System (DIDLS) for Historical Text Comprehension (HTC). The d...
Grammatiki Tsaganou, Maria Grigoriadou, Theodora C...
When a curriculum is proposed, it is important to verify at least three aspects: that the curriculum allows the achievement of the user's learning goals, that the curriculum i...
Abstract. In this paper we unify divergence minimization and statistical inference by means of convex duality. In the process of doing so, we prove that the dual of approximate max...
Using adaptive, personalized courses is rewarding, as it can create a better learning experience, tailored for a specific learner’s needs. The process of creating these courses,...