We introduce the problem of zero-data learning, where a model must generalize to classes or tasks for which no training data are available and only a description of the classes or...
This paper discusses how a new technology (designed to help pupils with learning about Shakespeare's Macbeth) is introduced and integrated into existing classroom practices. I...
Abstract—In this paper we present work on adaptive identification of learners’ strategies, gradually developing a higher level of adaptation based on evolving models of mathem...
This work represents the first step towards a task library system in the reinforcement learning domain. Task libraries could be useful in speeding up the learning of new tasks th...
James L. Carroll, Todd S. Peterson, Kevin D. Seppi
Recently, there has been an increased interest in "lifelong" machine learning methods, that transfer knowledge across multiple learning tasks. Such methods have repeated...